自动文摘的四种主要方法 (PDF download)

Document Sample
自动文摘的四种主要方法 (PDF download) Powered By Docstoc
					                                                                                           [×÷Õß                                                                                                                                                              ] Áõͦ£¬¿ªÖý
                                                                                           [µ¥Î»                                                                                                                                                              ] ¹þ¶û±õ¤Òµ´óѧ¼ÆËã»úÏ
                                                                                           [ÕªÒ                                                                                                                                                               ] ±¾ÎĽ«ÏÖÓе×Ô¶¯Õª·¨¸ÅÀË£ºÂ¼¡¢»ùÚíâ³éÈÍá¹
                                                                                           µÄ×Ô¶¯ÎÕª£¬²¢Ï긽éÉÜÁËâÖ·¨»ù±¾-ÀíÆÊöüÃÇÓÅãºÍ¡îóÐ
                                                                                           ÕªµÄÑо¿×´ö¡£
                                                                                           [¹Ø¼ü´Ê                                                                                                                                                                                                                                                                         ] ×ÔÈ»ÓïÑ´¦Àí£¬Ç鱨¿Æ§¶¯ÎÄÕª



                                                                                                                                                                                                                                                                                Ëùν×Ô¶¯ÄÕª¾ÍÊÇÀûÓüÆã»úµØ´-ÏÖÐÌáÈ¡£·«æ³
                                                                                                                                                             ijһÎÏ×ÖÐÚÈݵ¼ò½àÁ¬¹á¶Ì¡£
                                                                                                                                                                                                                                                                                ÔÚ׶¯ÎÄÕªÒÑß¹ý                                                                                                                                             40 ÄêÀúÊ·µ½ñÌ죬Ëü¼ÛÖ³äÏÔ¶ö´¡Õâ÷ÒªÓ¦¸Ã¹éÚç
                                         ×Ó³ö°æϵͺ¹ú¼Ê»¥ÁªøÂçÄÅî²·¢Õ¡£±´ó¿¶ÐνˮãÀò¬ÈÃÇ
                                         Ïëµ½ÁË×Ô¶¯ÎÄ¡£                                                                                                                                                                                                                                                                                                                                                                   1993 Äê                                           12 ÔÂÚµ¹ú           Wadern ÕÙ¿ªÁËÀúÊ·ÉϵÚÒ»´ÎÔ׶¯ÄÖ÷Ìâ¹
         ¼ÊÑÐÌֻᡣ   1995 Ä꣬¹ú¼ÊÆÚ¿¯                                                                                                                                                                                                                                                                                                                                                                                                                                                  Information Processing & Management ³ö°æÁËÒ»ÆÚÌâΪ
Summarizing Text µÄר¿¯£¬±àÕßÔÚÐòÑÖ¸³öâһưæê¾Å¶ÎªÊ´ú
ÒѾ-µ½À´            [1]¡£ÔÚÕâÖÇé¿öϬ¶Óеĸ÷ׯΪ·½¨øÜáʺ±ØÒ¡Ãæ
ÃÇÖðÒ»½éÉÜ×Ô¶¯ÕªÂ¼¡¢ùÓÚÀíâµÄÎÐÅϳȺÍá¹                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           4 Ö÷ÒªµÄ
ÎÄÕª·½¨¡£


                                                                                           1                                                                                                                                                                                                                                                                    ×Ô¶¯ÕªÂ¼

                                                                                           1.1                                                                                                                                                                                                                                                                                        ×Ô¶¯ÕªÂ¼µÄ²½ÖèºÍÒÀ¾Ý

                                                                                                                                                                                                                                                                     ×Ô¶¯ÕªÂ¼                                                                                                                                   (Automatic Extraction)½«Îı¾ÊÓªä×µÏßÐÔòÁ£¬½´
                                                                                                                                              ÐòÁ¡£Ëüͨ³·Ö                                                                                                                                                                                                                                                        4 ²½øУº (1)¼ÆËã´ÊµÄȨ֣»                                                                 (2)¼ÆËã¾ä×ÓµÄȨ֣»                                                (3)¶Ô-ÎÄÖеËùÓ¾ä
                                                                                                                                                                                         ×Ó°´È¨Öµ¸ßͽÐòÅÁ£¬îÄôɾ䱻·¶ÎªÕ                                                                                                                                                                                                                                                                                                                               (4)½«ËùÓÐÎÄÕª¾ä°´üÃÇ
                                                                                                                                                                                         ÔÚ-ÎÄÖе³öÏËòÊä¡£
                                                                                                                                                                                                                                                                                                                           ÔÚ׶¯ÕªÂ¼ÖУ¬ÆËã´ÊȨ¡¢¾äÑñÎĵÒÀÝDZ                                                                                                                                                                                                            6 ÖÐÎʽÌØÕ÷£º
                                                                                                                                                                                                                                                                                                                           (1)´ÊƵ                                                                           (Frequency)¡£Äܹ»Ö¸Ê¾ÎÕÂ÷ÌâµËù½ÓЧ´                                                                                              (Significant Words)ÍùÍÊÇ
                                                                                                                                                                                                                           ÖÐƵ´Ê¡£¸ù¾Ýä×Ó§Äöý¿ÉÒÔ¼ËãȨ¬ÕâÇ                                                                                                                                                                                                                                                                                     Luhn Ê×ÏÈÌá³öµÄÔ¶¯ÕªÂ¼·½
                                                                                                                                                                                                                           ·¨µÄ»ù±¾ÒÀÝ          [2]¡£ V.A.Oswald Ö÷Õžä×ÓµÄȨ¦°´ÆËùº¬ú±íÐÔ¡Ê®ýÁ¿À¼ã
                                                                                                                                                                                                          [3,4]£¬¶ø                        Doyle ÔòÖØÊÓ¹²ÏƵ¶È×î¸ßÄ¡°´±                                                                         [5]¡£ÃÀ¹ú                                                                                                                                                                                     IBM ¹«Ë¾ÔÚ   1960 ÄêÇ°ºóÑÐÖÆ ÁË
                                                                                                                                                                                                          Ò»Ì×ÎÄÕªÔ¶¯Éú²³Ðò                                                                  ACSI-Matic[3,4]£¬¸Ã³ÌÐòÔÚ¾äȨµÄ¼ÆËã·½æ¶                                                                                                                                                                                                                      Luhn µÄ·½¨øÐÁË
                                                                                                                                                                                                                            ¸Ä½ø¡£  1995 ÄêÃÀ¹ú                         GE Ñо¿Ó몷¢Öĵ                                              Lisa.F.Rau µÈËÍê³ÉÁ                                                                                                                                                                                             ANES(Automatic News
                                                                                                                                                             Extraction System)ϵͳ£¬¸ÃϲÉÓà¶Ô´ÊÆ×÷ΪÄ鬅                                                                                                                                                                                                                                                                                                                                         [6]¡£
                                                                                                                                                                                                                                   (2)±êÌâ      (Title)¡£±êÌâÊÇ×÷Õ߸ø³öµÄá¾ÎÂÚÈݶÓ﬽èÖúÍôí
                                                                                                                                                             (Stoplist)£¬ÔÚ±êÌâ»òСÖÞ³ý¹¦ÄܴʾßÓÒ°ãåµÃû£ÏºÍ-Î
                                                                                                                                                             ÈÝÍùÓнôÃܵÄÁªÏ£¬¿ÉÒÔ×÷Χ´Ê¡
                                                                                                                                                                                                                                   (3)λÖà      (Location)¡£ÃÀ¹úµÄ                                     P.E.Baxendale µÄ÷²é½á¹ûÏÔʾ£º¶ÎÂäÛÌâÇ×
                                                                                                                                                                                          ¾äµÄ¸ÅÂÊΪ                                        85%£¬ÊǶÎÂäÄ©¾µ¸Åª                                             7%[3]¡£Òò´Ë¬ÓбتÌá¸ß¦ÚÊâλÖõľä×Ȩ
                                                                                                                                                                                                     Öµ¡£




                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 e ÏßͼÇ飨    http://www.chinalibs.net£©                                   2003-11-8
                                                                                                                                                                                                                    (4)¾ä·¨½á¹                                                                 (Syntactic Structure)¡£¾äʽÓë×µÄÖØÒªÐÔ®¼´æÚųÁϬ±È
                                                                                                                                                              ÈçÎÄÕªÖе¾ä×Ó´ó¶àÊdzÂö£¬øÒÉ¡¢¸ÌÔò²»Ë½ë
                                                                                                       (Cue)¡£ Edmundson µÄÎÕªÏͳÖÐÓÒ»¸öԤȱàÆßË÷´Ê䣬                                                                                                          (5)ÏßË÷´Ê
                                                                                      3 Ö£ºÈ¡ÕýµÄ°Òå´Ê                   (Bonus Words)£¬È¡¸ºÖµÄ±áÒå´Ê                                                  ÏßË÷´Ê·ÖΪ                                                                                                                                                                                                                          (Stigma Words)£¬È¡Áã
                                        ÖµÄÎÞЧ´Ê                                    (Null Words)[7,8,9,10]¡£¾ä×ÓµÄȨÖÍÚÐÿ¸öÏßË÷´Ê®º¡                                                                                                                                                                                                                                                                                                                                       70
                                                  Äê´ú³õ£¬¶íº¥ÖÝÁ¢óѧµ                                             James A.Rush ½ÌÊÚºÍËûµÄѧÉú¿ª·¢Á                                                                                                                                                                                                                                                                                     ADAM(Automatic
                             Document Abstracting Method)ϵͳ¡£                                                                                        ADAM Ç¿µ÷ÄÊųâ¾ä×ӱ꼶ø²»Ñ¡Ôñ
                             ×¼£¬´Ê¿Ø±í                                              (WCL)Öдó¶àÊýÇ·ñ¨ÔµÄ                                               [11]¡£
                                                                       (6)ָʾÐÔ¶ÌÓï                       (Indicative Phrase)¡£ 1977 Ä꣬Ӣ¹ú                                                                                                                                                                                                                                                                            Lancaster ´óѧµÄ                    Palce Ìá³ö¸ù
¾Ý¸÷Ö¡°ÊÐÔ¶ÌÓï±À´ÑñÎÄժ䵷½¨                                                                                                                               [4]¡£ºÍÏßË÷´Êà±È¬Ö¸¾ÐÔ¶ÌÓïµÄ¿ÉÒªÇ
µÃ¶à¡£

                                                                                                           1.2                                                                                                                                                        ¶àÖ ÐÎʽÌØÕ÷µÄ×ÛºÏÀûÓÃ

                                                                                     ÉÏÃæÎÒǽéÜÁËı¾µ                                                                                                                                                                                                                     6 ÖÐÎʽÌØÕ÷£¬¼´º                                F-´ÊƵ¡¢                                     T-±êÌâ¡¢           L-λÖᢠ      S-¾ä·¨½á¹¡¢
                              C-ÏßË÷´Ê¡¢                                                              I-ָʾÐÔ¶ÌÓï¡£Õâ                                                                                                                                                                                                      6 ÖÌØÕ÷ÊÇ×Ô¶¯ªÂ¼µÄÒÀ¾Ý£¬ËüôӲ»Í½È¸ÁÎ
                              Ö÷Ì⣬µ«¶¼²»¹×È·Ãæ¡çûÄܽÉÏÊö¸ØÕ°ÓÐú±áºÆðÀ´ÒÔ
                                                                           W=f(F,T,L.S,C,I)×÷Ϊ¼ÆËã¾ä×ÓȨֵĹ«Ê½£¬ÇôÕÂÁ¿ÉÍûøÒ»²Ìá¸ß¡âØ
                                                                           ¼üÔÚÓº¯Êý                  f ÈçºÎ·¶¨¡£
                                                                                     Edmundson ÓÃÒ»¸ö¼òµ¥ÄÏßÐÔ·½³Ì                                                                                                                                                                                                                   W=a[,1]C+a[,2]K+a[,3]T+a[,4]L ½« 4 Ö»ù±¾µÄä
         ×ÓÑ¡Ôñ·½¨¼¯³ÉÚÒ»Æð                                                                                                                                                                                                                                                                         [7,8,9,10]¡£ W ´ú±í¾ä×ÓµÄîÖÕȨ£¬                         C ´ú±íÏßË÷Ê                    (Cue)Ȩֵ£¬                                                                      K
                                                                                  ´ú±í¸ù¾ÝÊƵ¼Ëã¶øÃĹØü                                                                                                                                                                                                      (Key)Ȩֵ£¬                 T ´ú±íÌâÃûÊ      (Title)Ȩֵ£¬                   L ´ú±íλÖÃ
                                                                                  (Location)Ȩֵ£¬                                                                                                                                                                                              a[,1]¡¢ a[,2]¡¢ a[,3]ºÍ a[,4]Êǵ÷½Ú²ÎÊý¡£ÕâÖ«»Í¬ÐÔÄÒòËؼ¥
                                                                                  µØÏßÐÔþ¼ÓÄ·½Êȱ¦³äÖÀíÉ£¬ùÃ÷²»¹ë¡Ú¾-ý                                                                                                                                                                                                                                                   10 ÄêµÌ½Ë÷Ö®ºó£¬
                                                                                  Edmundson ¶ÏÑÔ£º½ñóµÄÎժׯ»·¨±ØÐ뿼ÂÇý¾äÌ÷ÍÓïÒå¬ø²
                                                                                  Äܼòµ¥ØÒÀ´Ö²ÚͳÆÊý¾Ý¡£
                                                                                       Ä¿Ç°µÐí¶à×ԯժ¼ÏͳۺÁ˽ֻòÎÊÌØ÷¡£±Èç¬ÓÆÑó
                                                                                  (Nanyang)´óѧÐÖƵÄͼÊé¹ÝÂÎÅɾ½Úϳ                                                                                                                                                                                                                                                 (Library Newspaper Cutting System)£¬ÌṩÁË
                              ÌâÃû·¨¡¢Î»Ö¹Ø¼ü´ÊºÍ¸¾ÐÔ¶Óï                                                                                                                                                                                                                                                                                                             4 Ö×Ô¶¯ÕªÂ¼·½¨¹©Óû§Ñ¡ñ£µ«ÊÇÚàÌØ
                              Õ÷µÄ½áºÏ·ÃæÉдýîÈëѾ¿¡£
                                                                                                                                                                                                                    1997 Ä꣬ÈÕ±¾µ                                                                      Tadashi Nomoto µÈËÌá³öÁÒ»ÖùÓÚïÏ¿âÄ×Ô¶¯ÕªÂ¼·½¨¡£ûÃÇ
                              ½«Ò»ÅúÎÄÏ׷֪ѵÁ¼¯ºÍ²âÊÔ£¬¶ÐÿÆÚ¸ö¾äÓ¨¢°üÀ
                              ¡°¸Ã¾äÔÚÎıÖе»                                                                                                                                                                                                                                                            (Location in Text)¡±¡¢°ÓëêÌâÏà½üËƵij¶È                                                                                                     (Similarity to
                              Title)¡±µÈÊôÐÔļ¯£¬²¢ËΪؽ«¾ä×Ó·ÖÁÀàÒ»ÇÕí
                              ¾ä¡£È»ºóÔÚѵÁ·¼¯Äù´ÉϽ¨¢Í³ÆЬ¶²âÊÖÿ¸ö×ÓÇñܹ÷ΪÕÅ
                              ±ðÎÊÌ⣬½«×ª»¯ÒÀ¾Ýö²ß÷¶Ô¸ÃäøзÖàµÄ                                                                                                                                                                                                                                                                                                                           [12]¡£ÕâÖÉè¼ÆËÏëÊÇÔÚÓïÁ¿Ñ
                              ѧµÄÓ°ÏìÂÌá³ö£¬ËüÈüÆã»ú×Ô¶¯Ø´Á·Öи÷Õ½ºÊýΪà
                              ÌØÕ÷µÄ×ÛºÏÀûÓÿª±ÙÁËÒ»õз¡£«ÊǬÉÚü¾¹½¨¢ÔÎí²ãù
                              ´¡Ö®ÉÏ£¬È±·¦î¶ËùÒÔ¢Õ¹ÇÁ½«ÊܵÞÆ

                                                                                                           1.3                                                                                                                                                        ×Ô¶¯ÕªÂ¼µÄ²» ã

                                                                                                                                                                                                                    ×Ô¶¯ÕªÂ¼ËùÒÀ¾ÝµÄÊÇαнÉϹ棬ܴȺ»Æ²Í³ÌØ·û
                                                                                                           ÕâЩ¹æÂÉ£¬Òò´Ë×Ô¶¯ª¼ÄÜ»ÊÓÃÚ·ÇÏÞüͳöµÅã¡Èø¾ßÌåؽ²
                                                                                                           ƪÎÄÕ³£ÔÚЩʽÌØ÷ÉÏ·ûº¹æ¬¶øÁíÒ»¥´òßÇ
                                                                                                           µÄ³Ò»²¿·ÖûºÏ£¹æ¬¶øÔÚÁíÎ¥´ÕªÂ¼½áÜñס-ÐÈÝ
                                                                                                           ÎÄÕÂÔÚ¶à´ó³ÌÈÉÏ·ûº£¹æ¡Òòˬׯª¼µÖÊÁ¿Ü²»¨±Óý÷Ç
                                                                                                           ¹Ë´Ê§±£¬¶ÔÕâÒ»ÀàÎĵÐûºÃÁíÓÖ²î¡



                                                                                                                                                                                                                                                                                                                                                                                     e ÏßͼÇ飨                                   http://www.chinalibs.net£©           2003-11-8
                                                                                                                                                                                                                                                                                                                                                                 3 ·½ÃæµÄ²»×㣺
                                                                                                                                                                                                   (1)²»È«Ãæ¡£¶ÔÓÚàÖ÷ÌâµÄÎÏ׬¯ÕªÂ¼·½¨Éú³Ðʱö°üºÁË-ÅØ
                                                 ̸Â۵ijöÖ÷⣬¶øÔÓÚÆäËü·½ÃæÈÝ´»×²á°ÏìÁÎÕª«Ð¡ÊÇÉ
                                                 ÓÚ×Ô¶¯ÕªÂ¼È±·¦Îľ½á¹µÖöøì³É¡£
                                                                                                                                                                                                                                                (2)²»¼ò½à¡£×÷Õß³ÔÚÎÄÂÖе²Í¬ÃÓʾäظ´ÈÝ
                                                                                                  ÒÔ±ãÆðµ½Ç¿÷Ä×Óá£ÕâЩ¾ä¶¼Ê¹Øü¬ºÜÈÝÍøëΪ´ì³ÉÚ
                                                                                                  ÈßÓà¡£                                                                                                                                                               ACSI-Matic ³ÌÐòÊ×ÏȽÖÁËûýßÓàµÄ·¨¡£ü¶ÔÎÕª¾ä¼¯ºøì²é¬ç¹¸ö
                                                                                                  ÎÄÕª¾äÖе´ÊÓ                                                                                                                                                                 1/4 ÒÔÉÏÊÇàͬµÄ£ò¾³ýÆäÖл¡²ÓÃÕâ´Ú·½¨ºÜѶ±ð
                                                                                                  ³öÕæýµÄͬÒå¾ä£¶øÇÈç¹ûΪÖÐâÁ½¸×Ó¼±Ï¿úÌ«´ó
                                                                                                  ÁË¡£
                                                                                                                                                                                                                                                (3)²»Á¬¹á¡£³éÈÎÄÕÂÖеô¸ÉÔ-¾äתÒÍù±·¦òÊÇöÓ
                                                                                                                                                 »úµÄÕûÌ壬ÿҸö¾ä×Óͨ¹ýÊ¡ÂÔ¢Ö´Ï༰Úß-ØëÆÉÎ
                                                                                                                                                 ÈÚΪһÌå¡£µ±°ÑÄÕÂÖвͬÃÉϳöô¸¹Ø¼ü¾äÁ׺¶Êâ©Ó
                                                                                                                                                 ÍÑÀëÁËÉÏÂÎĶøÒÔ׼ȷµØí½â¡£¬Ê±¾äÓÖ®Ú¦ß-´ÐòÃÞÕ
                                                                                                                                                 ·¨ÔÚÕû¸ö¶ÎÂäÖй³Éƽ»¬µÄÅîÁ÷¡£ÓçâÑùʱèÒªø²ºÍÀí«
                                                                                                                                                 ¼ÓÖØÁ˸ºµ£¬Ðʱ»¹¿ÉÄÜóöëÔ-β·ûÛã¡
                                                                                                                                                                                                                                                Rush Ê×ÏȶÔÎÄÕªµÁ¬¹áб꼸øÓèÖØ¡£Ú                                                                                                 ADAM ϵͳÖУ¬Èç¹ûĸöÎÕªºòÑ¡¾äèÒ
                                                                                                                                                 ÓÐÒ»¸öÏÈ´Ê£¬ÄÇÃÎÚ¾ä°æµý×¼¹¨ÖºÜͲªÑ¡ëÕ¶ø±¤
                                                                                                                                                 Öв»³öÏÓÉÚȴʶª§øÔìµÄÁî˷ѽâó¡£                                                                                                                                                                                                                   ADAM ϵͳÊÇÈËôÓ×Ô¶¯ÕªÂ¼òÎÄ
                                                                                                                                                 ÕªÂõ³öµÄÚÒ»²½                                                                                                                                           [3,4]¡£
                                                                                                                                                                                                                                                Mathis ÊÇ                                                Rush µÄѧÉú£¬ËýÐÖÆÎÕªÏͳܹ»ÔÚ´ÊŶ¨¡¢ÌÓï±ðº×¾ä
                                                                                                  »ù´¡ÉÏ£¬Í¨¹ý²¢ÁÐÊÓôµÈ½«¸ö¾ßàÖ÷òÎļ¥äéªÒ
                                                                                                  ¸´ºÏ¾ä¡£ÃµÍ³»¹ÄܨýÐÞ×ÓÖÆËüàØÁª¶ÌÊøû¼²ÎÕ¬
                                                                                                  ¶ø½Ò»²¸ÄÉÆÎÕªµÁ¬¹áÐÔ                                                                                                                                                                                                                                   [3]¡£


2                                                                                                                                                                                                                                               »ùÓÚÀí½âµÄ×Ô¶¯Î Õª

                                                                                                                                                                                                   »ùÓÚÀí½âµÄÎÕª·¨ÊÇÒÔÈ˹¤ÖÜ£¬Ìرð×ïѼõ´¡¶ø¢Æ
Õª·½¨¡£âÖÓë×Ô¶¯Â¼µÄÃ÷ÏÇø±ðÚÊÀû¬Ëü²»öïѧñÈ
ÓïÑԽṣ¬¸üÖØÒªµÄÊÇÀûÃÁìò¶øÐÅÏ¡¢ÍÆíÎÕâå±¾×îºó´
±íʾÖÐÉú³ÕªÒ¡£

2.1                                                                                                                                                                                                                                                                               »ù±¾²½Öè

                                                                                                                                                                                                   »ùÓÚÀí½âµÄ×Ô¶¯Îժͨ³£ÐÒϲÖèº
                                                                                                                                                                                                   (1)Óï·¨ÖÎö¡£½èú´ÊµäÐÄÓÑÔ§ª¶-¾×ø¬»ñÃá
                                                 ¹Ê÷¡£
                                                                                                                                                                                                                                                (2)ÓïÒå·ÖÎö¡£ÔËÓêʶ¿âеĽ«¨á¹è×»³ÉÂß¼-ºÍù´
                                                                                                  µÄÓïÒå±íʾ¡£
                                                                                                                                                                                                                                                (3)ÓïÓ÷ÖÎöºÍÐÅÏ¢ÌáÈ¡£¸ù¾ÝªÊ¶¿âÔ¤´æµÄÁìòÚɽøÆÀí¬
                                                                                                                                                 ²¢½«ÌáÈ¡³öÀ´µÄ¹Ø¼üÚÝæëÒ»ÕÅÐϱí£
                                                                                                                                                                                                                                                (4)Îı¾Éú³¡£½«ÐÅÏ¢íÖµÚÈÝת»ÎÒ¶ÍêÕûÁ¬¹áÊäö

2.2                                                                                                                                                                                                                                                                               ƪÕÂÒâ åµÄ»ú Ú±íʾ

                                                                                                                                                                                                   ƪÕÂÒâåµÄ»úÚ±íʾÇÔ-ηÖö½á¹ûºÍɳÀÝ£¬ËüùÓÏ
Öд¦ÓÚÊàµØλ¡£²Í¬Ï³ÉÃÄƪÕÂÒâåú±í¾Ëù


                                                                                                                                                                                                                                                                                                                                                                                             e ÏßͼÇ飨                          http://www.chinalibs.net£©   2003-11-8
                                                                                                                                                                                                                                                                                                                                                                                     2.2.1 ½Å±¾                                             (Script)
                                                                                                                                                                                                                                                                                                                                                                                     70 Äê´ú©                    80 Äê´ú³õ£¬ÃÀ¹Ò®Âóѧµ                                                         Schank Ôڽű¾µÄ»ù´¡ÉÏÑÐÖÆÁË                                                                  SAM(Script
                                                                                                                                                                                                                                          Applier Mechanism)ϵͳ¡£¸ÃÏÓ¦½Å±¾·ÖÎö¼ò¥Ä¹Ê¬ÔÚ´Ë»ùɶøÐ×Üá
                                                                                                                                                                                                                                          [14]¡£
                                                                                                                                                                                                                                                                                                                                                                 ÃÀ¹úҮ³´óѧµÄ                                                                DeJong ÓÚ 1979 ÄêÑÐÖÆÁËøÃûµ                                                                FRUMP(Fast Reading Understanding
                                                                                                                                                                                                                                          and Memory Program)ϵͳ£¬¸ÃÏÓÚ¿ìËÙÔÄÀ¢ÎÐÂÅ×ÊÁÇí½âÕªÑù°å¡
                                                                                                                                                                                                                                          FRUMP ÓÉÔ¤ÑÆ÷ºÍéÖÁ½²¿·×³¡£Àûù¸Å¾ç±âµÇ°ÐÎÏÂÄÜöÒ»
                                                                                                                                                                                                                                          ¸ö»òÒ×éʼþ£¬ÑÖ¤Æ÷µÄÈÎñÇ¥ÕâЩ±Ô²¢ø³ÅÏ¡                                                                                                                                                                                                                                                                                                              FRUMP µÄÓ¦
                                                                                                                                                                                                                                                                                 Ó÷¶Î§ÊÜÄÚ²¿´æ¢µ¹£¸Å¾ç±ÏÞÖƬÈûÕÂлͳËùÝÔò¨Éú
                                                                                                                                                                                                                                                                                                                              ºÎÕªÒ£¬»áÓбóµ¼ÔÖÂÍûÄÉúå¿Ü                                                                                                                              [15]¡£
                                                                                                                                                                                                                                                                                                                                                                                2.2.2 ¸ÅÄî´ÓÊô½á¹                                                               (Concept Dependency Structure)
                                                                                                                                                                                                                                                                                                                                                                                ÃÀ¹ú           J.I.Tait µÄ Scrable ϵͳ¶Ô                                                         FRUMP ϵͳ½øÐÁ˸ģ¬üÒªÇóÊäÈë×ÔÚ´¦Àí
                                                                                                                                                                       Ç°ÏÈת»³É                                                                                                                                                                                                                CD(Conceptual Dependency Structrue)½á¹£¬ÔÚ´Ë»ù¡ÉÏ·ÖÎöºÍȶ¨±¤²â
                                                                                                                                                                                 µÄÐÅÏ¢ÓëδԤ²âÖ®¼ä¹Ø£¬½«ÕÁ¿·ºÀí×鯳ÉһƪÍêûá
                                                                                                                                                                                                                              Õª¡£È»¶øÓÉÚ                                                                                                                                                                      CD ½á¹ýÓÚ¸´Ô£¬ËùÒʵÏÖÆðÀ§ÄÑó                                                                                                 [15]¡£
                                                                                                                                                                                                                                                                                                                                                                 2.2.3 ¿ò¼Ü                                                                 (Frame)
                                                                                                                                                                                                                                                                                                                                                                 80 Äê´ú©£¬ÃÀ¹                                                                  GE Ñо¿Ó몷¢Öĵ                                Lisa F.Rau µÈÑÐÖÆÁË                                                       SCISOR ¸ÅÄîÐÏ¢Ëõ´¡
                                            ×éÖ¯ºÍ¼ìË÷ϵ³                                                                                                                                                                                                                                                                                                                                                        (System for Conceptual Information Summarization,Organization and
                                                          Retrieval)¡£ SCISOR ÊôÓÚµäÐÍÄÀí½âÎÕª£¬Ëü´¦¶ÔÏóǹء°«¾º²¢±ÂŨ
                                                                                                             µ¼¡£                                                                                                                                                                                                                                        SCISOR Ê×ÏȲÉÓùؼü´ýÂ˺ÍÄ£½Æ¥Åäµ·¨¶Ô¦ÀíÎøÐÖ÷Ìâö¬Ò±ã
                                                                                                                  ¸Ã±¨µÀÄÚÈÝÊÇ·ñÓë¡°¹«Ë¾ºÏ²¢ÐØ£»óÉÁìòÎÞ×ÔÖöÆ÷
                                                                                                                                                              TRUMP(TRansportable Understanding Mechanism Package)ʶ±ðÿ¸ö¾ä×ӵĽṣ¬Éú³Àà
                                                                                                                                                              ËÆÓÚ¿ò¼Ü                                                                                                                                                                                                                        (Frame)µÄ¸Åî±íʾ£»×ºóÔËÓö¥Ïòµ¤ÆÚÇý¯·ÖÎö÷                                                                                                                                     TRUMPET(TRUMP
                                                                                                                                                                       Expectation Tool)´Ó¸ÅÄî±íʾÖÐÌáÈ¡Ô¤ÆÚµÝ                                                                                                                                                                                                                                                                                                                        [16,17]¡£
                                                                                                                                                                                                                                                                                                                                                                 80 Äê´ú³õ£¬µÂ¹¿ËÌóѧ                                                                                            Hahn µÈËÑÐÖÆÁ                                             TOPIC ϵͳ£¬¸ÃÕë¶Ô΢´¦ÀíÆ÷
                                                          ÁìÓòµÄ¿Æ¼ÎÏ×£¬ÒÔÜ÷ªÖʶ±í¾»ù´¡Í¨¹ýÈ«ï·åöÉú³²¤
                                                                                                       µÄÕªÒ                                                                                                                                                                                                                                                                          [18]¡£
                                                                                                                                                                                                                                                                                                                                                          2.2.4 Ò»½×δÊ
                                                                                                                                                                                                                                                                                                                                                          Òâ´óÀû                                              Udine ´óѧµÄ                                      Danilo FUM µÈËÔÚ                                      80 Äê´ú³õÑÐÖÆÁË                                 SUSY(SUmmarizing System)
Ëõдϵͳ£¬¸ÃÒÔ»½×ÎÊÂß¼-ªù¡ÈÁºÄ§¹ûÌåÖö·¨Ç±
Á¦¡£
                                                                                                                           SUSY ϵͳÓÉÁ½²¿·Ö×é¡£ÚÒ»ÆΪ¸Ùú÷                                                                                                                                                                                        (Schema Builder)£¬ËüÊÕ¼¯Óû§Ðè
Çó£¬ÐγÉÕªÒ¸Ù                                                                                                                                                                                                               (Summary Schema)ºÍÎı¾¸ÙÒª                                                                                     (Text Schema)¡£µÚ¶þ²¿·Ö°üÀ¨ÎöÆ÷
(Parser)ºÍËõдÆ÷                                                                                                                                                                                                            (Summarizer)¡£·ÖÎöÆ÷×ÔµÏòÉØ-Ĭ½¨Á¢ðÒ»´ÊÐú
              ÄÚ±íʾ¡£ËõдÆ÷×ÏȹÓÃθÙÒªºÍ¼¨æÔò²úɵ¿¬»óÕ
                                                        Ñ¡Ôñ¹æòÐÞ¼ôÓȨµÄÚ²¿±íʾ£¬×îºó´äëÎÖìË÷³ö»ù¥ª¢¶ÌïÕû©
                                                                                                           ½«ËüÃÇ×°Åä³ÉÕªÒ                                                                                                  [19,20]¡£

                                            2.3                                                                                                                                                            Àí½âÎÄÕªµ ²»×ã

                                                                                                                                         Àí½âÎÄÕªµ²»×ãÔÚÓÁìòÑϸñÊÜÞ¡£³É-Òº
                                                                                                                                         (1)ÃæÏò´ó¹Ä£ÕʵÓïÁ·¨ÒåÖÎö¼õÉÐÍêÈ«³ì¬Ëçûë»ñø߿
                                            µÄÓïÑÔ·ÖÎö½á¹û£¬¾Í±ØÐë«´ý¦ÀíÁÏÞÆÚ³¸¶§®¡
                                                                                                                                                                             (2)Àí½âÎÄÕª·¨µ»ù´¡ÊÇ¿ò¼ÜÈÖ¶±¾£¬ÐèÒ¸ÝÁìÓÔ¤ÏË
                                                                                      Èç¹ûÏë°ÑÊÓÃÚij¸öÁìòµÀí½âÎÕªÍÆãÒ»£¬ÔÐèÖض¨¿¼ÜÌîä
                                                                                      ºÍ×éÖ¯ÁìÓòªÊ¶µÄ³Ø¸£¹Àí½âÎÕÑÒÔƲ¡




                                                                                                                                                                                                                                                                                                                                                                 e ÏßͼÇ飨                                            http://www.chinalibs.net£©                                                                                                      2003-11-8
                                                                                                  3                                                                                                                                                ÐÅÏ¢³éÈ¡

                                                                                                                                                                                                    »ùÓÚÀí½âµÄÎÕª·¨ÐèÒ¶ÔÂøÈ«ÃæÖö£¬Éú³Ï꾡ïå±´ó¹
                                                                                                  Ä£Õæʵα¾¶øÑÔǺÜÏÖ¡Óë®àȬÐÅ¢³é                                                                                                                                                                                                                                                                                       (Information Extraction)Ö»¶ÔÓÐÃ
                                                                                                  µÄα¾Æ¬¶½øÐÓÏÞÉîÈ·Öö£ä§ÂʺÍÁé»ÔÌá¸ß¡
                                                                                                                                                                                                    ÐÅÏ¢³éÈ¡µÄ×Ô¶¯ÎÕªÒ¿ò¼Ü                                                                                                                                           (Abstract Frame)ΪÖÐÊ࣬·ÎÑ¡ÔñÓëÉú³Á½¸ö×
                                                                                                  ¶Î¡£ÄÕª¿ò¼ÜÊÇÒ»ÅÉêëµ¥¬ËüÔ²ÛнÌá³öÓ¦´-Öñȸ÷ÏîÚÝÀýç
                                                                                                  ¶Ô¼ÆËã»ú²¡¾ÀàµÄÎÕ¿ÉÒÌá³öÈçÏòÜ£º
                                                                                                                                                                                                    ²¡¶¾£ûóƺ
                                                                                                                                                                                                                                                                        ²¡¶¾´«ÈÔÏó£º
                                                                                                                                                                                                                                                                        ²¡¶¾ÀàÊô£º
                                                                                                                                                                                                                                                                        ²¡¶¾¹¥»÷ÔÏó£º
                                                                                                                                                                                                                                                                        ¡-£ý
                                                                                                                                                                                                    ÔÚÑ¡ñ½×¶Î£¬ÀûÓÃÌØÕ÷´Êı¾ÖгéÈÏ๵ï»òä¼Üýç
                                                                                                  ±¾Öз¢Ï¡°-¸È¿É´Îļþ×Ñù£¬ÔòÒ½«ÌØÕ÷ʺóÃ浶Óï
                                                                                                  ÐÎļþ¡±×÷ª²¶¾µ¸ÈÔÏóÌîëÕ¿òÜ£
                                                                                                                                                                                                    ÔÚÉú³½×¶Î£¬ÀûÓÃÄÕª°å«¿ò¼ÜÖеÈÝ»Êäö¡Ç´ø
                                                                                                  °×²¿·ÖµÄϳÉÌ»£¬ÆäÕÓëΪò¼ÜÐÛà¶Ô¦¡ÀýÈç¸Ã¾
                                                                                                  ÏóÊÇ£¨²¡¶¾´«ÈÔ©±Ä°åÖеһ¸öä×Ó¬òΪÚÕ¿¼Ü
                                                                                                  ¡°¿ÉÖ´ÐÎļþ±£¬ÒòËÔÚÕª½«Êä³öâÑùµ¾×Óº¸Ã²¶ÈÏóÇ
                                                                                                  ¼þ¡±£
                                                                                                                                                                                                    Ó¢¹ú                                                                                           Lancaster ´óѧ      Paice µÈËÔÚ                                         1993 ÄêÌá³öµÑ¡ÔñÓëÉúÎÕª·¨£¬ÊÖϾÍÇÐÅ
                                                Ï¢³éÈ¡·½¨£Ä¿Ç°¸ÃµÍÖ÷ÒªÕë¶ÔÐÂóÊѱæά«¾ßýÚÅÁ¦¹ËüÜ
                                                ¹»·½±ãµØÒÆÖ²äËüÁìÓò                                                                                                                                                                                                                                                 [21,22]¡£Ó¢¹úÂü³ËÌØµÄ                                                                          Black ÊÇ     Paice µÄºÏ×÷Õß         [23]¡£
                                                                                                                                                      ÓÉÚÎÄÕª¿ò¼Üµ±àдÍêÈ«ÒÀÁìÖʶ£¬ËùÔÅÏ¢³é¡»ÇÞƲ
¹ýÎÄÕª¿ò¼Ü±ÈÀí½âÖеžҥö࣬¸ü×ÓÚ´¡Ï¢³é¦öÁì
Óò£¬¾Í±ØÐëΪÿ¸öÁ춼à´Ò»ÄÕÜÔÚ¦ÀíÊÏȽøÖ÷Ìâðùݵ
ÓÃÏ঵ÄÎÕª¿ò¼Ü¡£ÁíÍ⬥ƾÌØ÷´Ê»¶ïá×Àî³ä²¢Ç·
׼ȷµÄ£¬¶øÇÒÓÉÚïÑÔÁé»îàùЩÛÖα¾Æ¿ÜÃ÷ÏÌØÕ¡ºó
ÓÉÚʹÃÄ£°åú³ÎÕª¬µÂïÑÔǧÆÒ»®·Ö´ô¡


                                                                                                  4                                                                                                                                                »ùÓڽṠµÄ×Ô¶¯Î Õª

                                                                                                                                                                                                    ƪÕÂÊÇÒ»¸öÓÐúµÄ½á¹Ì壬ֲͿ·³×ŦÜ÷®¼ä´æÔÚ
                                                                                                  ´í×Û¸ÔӵĹØÏ¡£ÆªÕ½á·ÖÎöÇå³þÁˬºÐ²¿È»ÜÒ«Êïѧ¶Ú
                                                                                                  ƪÕ½ṵÄÑо¿»ºÜ²£¬ÉÓÃÎÊæÔò͸üÙÁËâùÚ׶¯Ç°
                                                                                                  Ϊֹ»ÃÓÐÒÌ׳ÉÊìµÄ·½¨£¬²ÍѧÕßÀ´¶±ðÆÂáºÜóî¡

                                                                                                  4.1                                                                                                                                                                                   ¹ØÁªÍøÂç

                                                                                                                                                                                                    Èç¹û½«Ò»¸öÓïÑÔµ¥ªÄ÷×ÊÎÚ㣬²¢ÁÐåÏÖ®¼äý
                                                                                                  Ìõ±ß£¬ÄÇôÎҾ͵½ÁË»¸ö¹ØªøÂç¡ÔÚÖÐÓëãÏàÊý³Æ
                                                                                                  ¶È¡£½ÚµãÄÔ´ó¬òÍøÂçÖÐØÒª¸ß«×îôÉÓ¥³éöÀ¼
                                                                                                  ¿É¹³ÎÄÕª¡£
                                                                                                                                                                                                    Ç°ËÕÁªµÄ                                                                                            E.F.Skoroxod¡ä             ko ½«ÎÄÕÂÊÓª¾ä×µ¹ØÁÍø磬¼Ï¨¢ÔÚ´
                                                ͬÒå¹Øϵ»ù´¡Ö®É£ºÜ¶à¾ä×Ó¼ÐÁªÄ±È·ÎÕ                                                                                                                                                                                                                                                                                                                                                         [4]¡£ÃÀ¹ú   Cornell ´óѧ



                                                                                                                                                                                                                                                                                                                                                                                                                 e ÏßͼÇ飨     http://www.chinalibs.net£©      2003-11-8
                                                                                                                                                                                                                                                                                                                                                                 Salton µÈËÔò½«ÎÄÕÂÊÓª¶ä¹ØÁÍøç¡£Ï×ÖÐÿ¸ö±»³èÒÌ÷¬
                                                                                                                                                                                                                           ¸ö¶ÎÂäÌØÕ÷ÏòÁ¿µÄÚ»ýת⽹ÇÈ¡£çû³¬ø¨ãÐ
                                                                                                                                                                                                                           Öµ£¬ÔòÈÏΪÁ½¸ö¶ÂäÓÐïÒ塺ÍÜà¼Ä±»Ìá³À´×éÉÆ
                                                                                                                                                                                                                           ÕªÒ                                                                                                                                                              [24,25,26]¡£
                                                                                                                                                                                                                                                                                                                                                                                             ¶ÔÓÚƪ·ù½Ï³¤µÄÎÕ£¬¾ä×Ö®¼¹ØÁÍøç«ÊÅ´ó±¿úÇÑÒÐÜ
                                                                                                                                               µÄ¡£Ïà±È֮¬¶Îä¼¹ØÁªÍøçÒÐÃíâºÓɾ×é°ÆðÀ´Õ
                                                                                                                                               ¶ÎÂäÆ´½ÓðÀµÄÕªÁ¬¹áÐÔÏÖø̸ߡ£²»ýÉÚ×îØÒ¿Ü°üº©Þô
                                                                                                                                               ÒªµÄ¾ä×Ó£¬ËùԻڶγéÈ¡ÕÏò¹«Á·

                                                                                                                                                                                                                           4.2                                                                                                                                                                                                                                                                                   Ð޴ǽṠ                                                                                     (Rhetorical Structure)

                                                                                                                                                                                                                                                                                                                                                                                                                                                90 Äê´ú³õ£¬ÈÕ±¾                                                                                                                                                  Toshiba ¹«Ë¾µÄ                                             Kenji Ono µÈ»ùÓÚÐ޴ǽá¹Ñ¾¿×Ô¶¯ÎÄÕª¡£Ëûë
                                                                                                 ´Ç¹ØϵéÄÉΪ¾ÙÀý£¼                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             EG£¾¡¢Ô-Òò£¼                                  RS£¾¡¢×ܽ᣼           SM£¾µÈ                                          34 Ö£¬Ê×ÏÈÒÀ¾ÝÁ½Ó´µÍƼ³ö»
ÖÀàËÆÓھ䷨Ê÷µÄÐ޴ǽṣ¬È»ºó¶Ôø¼ô«±ÁÏÂݸùüÃ
Ö®¼äµÄÐ޴ǹØÏ×鯳ÉһƪÁ¬áÎÕ                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  [27,28]¡£ÕâÖ·½¨µÄ²»×ãÔÚÓºÐ޴ǹØÏʶ±ðÒÀ
ÀµÓÚÁ¬½´Ê£Èç¹ûÎÄÕÂÖÐý¿ºÜÉÙÇÃÞØϾͷ¨¶±ðË¡

                                                                                                                                                                                                                           4.3                                                                                                                                                                                                                                                                                   Óï ù¦ÄÜ

                                                                                                                                                                                                                                                                                                                                                                                                                                                ÕâÖ·½¨÷ÒªÊÇë¶Ô¿Æ¼ÎÄÏס£µÐ´Ó±ÈѸñ¹æ¬²»Í
                                                                                                                                                                                                                                                                      ³Ðµ£×Ų»Í¬ÄÓïù¦Ü¸ù¾Ý¿ÉÒÔ½«ÎÕÂÖ÷Ìå·Ê¶±ðöÀ´ª¡
                                                                                                                                                                                                    1978 Ä꣬Ô-½Ý¿Ë¹Âå·¥²¼À¸ñµ                                                                                                                                                                                                                                                                                                                                                                                                                                                       Jiri Janos Ìá³öÁËÒÀ¾Ý¹¦ÄÜä×ÓÛ                                                                                 (Functional
                                                                                                                                                                                               Sentence Perspective,FSP)ÀíÂÛ½øÐÎı¾Å¨Ëõµ·¡£                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               FSP ÊDz¼À-¸ñѧÅÉÂíÌ©ÐÝ˹
                                                                                                                                                                                               (Mathesius)µÈËÌá³öµÄÒ»ÖÓïƪÀíÂÛ£¬                                                                                                                                                                                                                                                                                                                                                                                                                                 Jiri Janos ²ÉÓøÀíÂ۵ĿÊÇΪÁËͨ¹ý¶Ô¾ä×
                                                                                                                                                                                               Óïù¦Äܵ·ÖÀཫα¾÷¸É£¨³Æª                                                                                                                                                                                                                                                                                                                                                                                                                                      Text Proper£©ºÍÖ¦Ò¶£¨³ÆΪ                                                                                     Metatext£©Çø±ð¿ªÀ´¡£
                                                                                                                                                                                                                                                                      Îı¾µÖ÷¸ÉÓÌâ                                                                                                                                                                                                                                                                                                                          (Theme)ºÍÊöÌâ                                  (Rheme)¹¹³É£¬ÒÔ²»ÍµÄÖ÷Ìâƽø·Ê                                                                                        (Thematic
                                                                                                                                                                                                                                                                                                                     Progression,TP)Ï໥Ïνӡ£Ö÷¸ÉÊÇÐèҪصã·öºÍÕ¼ÄÚÈݬ¶ø¦Ôò¿Å³ý
                                                                                                                                                                                                                                                                                                                     Ö®Íâ                                                                                                                                                                                                            [29,30]¡£
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      ÈÕ±¾º£µÀ´óÑ§Ä                                                                 Maeda ½«¾ä×ÓµÄÐÅÏ¢¹¦Ü·ÖΪ£º±³°                                                   (B)¡¢Ö÷Ìâ                   (T)¡¢·½¨                                                              (M)¡¢½á
                                                                                                                                                                                                                                                                                                                          ¹û (R)¡¢Àý×Ó                                                                                                                                                                                                                                                           (E)¡¢Ó¦Ã          (A)¡¢±È½Ï                               (C)ºÍÌÖÂÛ             (D)£¬²¢ÈÏΪ     T¡¢ M¡¢ R ºÍ D ÊÇÖ÷¸É£¬Ó¦½øÈëÎÄ
                                                                                                                                                                                                                                                                                                                            Õª£»                                                                                                                                                                                                     E¡¢ A¡¢ C ºÍ B ÊÇÖ¦Ò¶£¬ÓųýÔÚÎÄÕª®Íâ                                                                                                         [31]¡£ÃÀ¹úŦԼ        Syracuse ´óѧµÄ                                                                              Liddy ͨ¹ý
                                                                                                                                                                                                                                                                                                                                 ¶ÔÈ˹¤ÎÄÕªµ´óÁ¿÷²éɳö¾-Ñ                                                                                                                                                                                                                                                                                                                    (Empirical Abstract)µÄ»ù±¾½á¹£º³°¡ª¿µ
                                                                                                                                                                                                                                                                                                                                                          ·½¨¡ªá¹ûÂÛ¸¼£¬ÆäÖÐÿһÏîÄÚÈÝÓ°üÀÁË©Ôò                                                                                                                                                                                                                                                                                                                    [32,33,34]¡£Èç¹û½«ÎÄÕª
                                                                                                                                                                                                                                                                                                                                                                                                Öгµ£Õ⩹¦ÄÜƬ¶ÎʱðöÀ´¾Í¿ÉÒÔ×骡
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    ºÍÓÃÆäËü·½¨Éú³µÄÎÕªÏà±È£¬¸ù¾Ý﹦ÜÌáÁ¶öÀ´û¿¼×
                                                                                                                                                                                                                                                                                                                                                                                                                                 дµÄ±ê×¼¡£Èç¹ûÏë°ÑÕâÖ·½¨ÍÆã¿ÎÒÔ¾¥¬ò誶¸÷ÀàÂá
                                                                                                                                                                                                                                                                                                                                                                                                                                                                              ÉîÈëÑо¿¡£Æäʵ¼´¹ÇÎÄÏ×Ò²Ó¸÷ÖÀàͬíÂÛÕ¢éºö½áø
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          ±ðÒ²ºÜ´ó¡£


                                                                                                                                                                                                                           5                                                                                                                                                                                                                                                             ÖÐÎÄ×Ô¶¯ Õªµ Ñ ¾¿ ´ ö

                                                                                                                                                                                                                                                                                                                                                                                                                                                ÎÒ¹ú´Ó                                                                      1985 Ä꿪ʼ½éÉܹúÍâ×Ô¶¯ÎÕ·ÃæµÑоÇö                                                                                                                                                                                                  [35]£¬´Ó       80 Äê´ú©¿ªÊ¼Ñо×Ô
                                                                                                                     ¶¯ÎÄժʵÑéÏͳ£¬ÖÁ½ñÒ²ÓÐ                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            10 ÓàÄêµÀúÊ·ÁË¡£
                                                                                                                                                                                                                                                                                                                                                                                                      ÔÚÐÎʽÌØÕ÷·Ã棬ºÓïÍÄÖÒªÇø±ð´¼ä»¿¸ñò¶×ů
                                              Ìâ¡£ºÓï×Ô¶¯·Ö´ÊÇÒ»Ïî¾-¹ýàÄêÑпÈβÂú½öµ¬Ú©ó§Å¢ÜÀí
                                              µÄÀîÃ÷Ìá³öÁË´Óº×ÖÆÂÊͼ·¢È¡ÎÕª¨Ò®£¬¶ø»Ø±ÜÔ¯â                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             [36]¡£È»
                                              ¶øÒòΪºÓïÖÐÕæý¸ÔØÅÏ¢µÄÊÇ´²»×£¬ËùÈç¹û·¼õÜÂúãó±¾


                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       e ÏßͼÇ飨                                    http://www.chinalibs.net£©           2003-11-8
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              80 Äê´ú©¾Í¿ªÊ¼ÑÐ×Ô¶¯ÕÂ
                                                                                                                                                                                                           Êõ£¬                                                  1997 ÄêÑÐÖÆÁË                                                                    OA ÖÐÎÄÏ×Ô¶¯ÕªÒµÍ³¡£¸Ã¼ÉÁË»·¨¢Ê¾ÌÓï¹Øü
                                                                                                                                                                                                           ´Ê·¨ºÍ±êÌâµÈ¶àÖ½£¬ÇÒ»¸öÓÃÄϳ                                                                                                                                                                                                                                                                                      [37,38,39,40]¡£
                                                                                                                                                                                                                                                                     ÔÚÓïѵÄÉî²ã½á¹·Ã棬º´Ò»Ð©±ðÎ÷ÌØ¡Èç¦Êä
                                                                                                                                                    »¯£¬Ôö¼ÓÁ˾䷨ÖεÄѶȺïÐÒ©ÌØÊâ½çæ¡¢²ÉÃÀí
                                                                                                                                                    Ñо¿ÖÎÄÕª£¬±Øë³ä·¼ÂǺÓïµÌã¡                                                                                                                                                                                                                                                                                                                   80 Äê´ú©£¬ÉòÑô¶«±ó§Ò¦Ìì˳½ÊÚºÍÏã¸ÛÇ
                                                                                                                                                    ÊÐÀí¹¤´óѧÁªºÏ¿ÕË¡°ÖÎÄÈ«×Ô¶¯ÒµÍ³±¾£¬¸Ã²ÉӽŨ
                                                                                                                                                    ¹ýÓëû§½¥ñÈ¡ÎÄÕª                                                                                                                                                                                                                       [19,41]¡£                                    1990 ÄêÇ°ºó£¬ÖпÆÔÈí¼þËùµÀõ¢ì½Ú¾©´
                                                                                                                                                    ѧÂíÏ£ÎĽÌÊÚµÖ¸¼¬¶ÔӢׯժøÐÁ˾¿²ÆÒ»éͳ¡
                                                                                                                                                    EAAS(English Automatic Abstract System)¡£¸ÃϵͳÊÇÒ»ö±ê×¼ÄÀí½âÎÕª¬Ëü¾ÖÞ
                                                                                                                                                    ÓÚ¡°¾ÍÒµ»úá½éÉܱÕâÑù¸öÁìò£Ï³Ê×Ȩ¹ýëç¥ñÐŢ㼯¬ºó¶ÔÎÄ
                                                                                                                                                    Õ½øÐÓï·¨ÒåÖÎö£¬Éú³Äâ¿ò¼Ü                                                                                                                                                                                                                                                                                                                amf£¬½Ó×Å°´ÕÐÏ¢¹µã¼¯                                                                                   amf ÖÐËÑ÷ÍÆÀí³ö
                                                                                                                                                                                                           ÓйØÅÏ¢£¬×îºóÉú³Ò»¶¨Âß¼-ÔµÄÎÕª                                                                                                                                                                                                                                                    [15,42,43]¡£
                                                                                                                                                         ¹þ¶û±õ¤Òµ´óѧͿªÖý½ÌÊÚÓ                                                                                                                                                                                                                                                                        1992 ÄêÑÐÖÆÁË»ùÓÚ×ÔÈïÀí½âµÎÕªÊéÏͳ
                                                                                                                                                    MATAS[44]£¬                                                                                                                                              1994 ÄêÑÐÖÆÁË×Ô¶¯ÕªÂ¼Àൠ                                                                                                                                                       HIT-863¢ñÐÍ×Ô¶¯ÎÄժϵ³                                                                            [41]¡£            1996 Äê±ÊÕßÌá
                                                                                                               ³öÁË»ùÓÚÐÅÏ¢éÈ¡ºÍÎı¾Éúµ×Ô¶¯Õª·½°¸                                                                                                                                                                                                                                                                                                                                                [45]£¬                                       1998 ÄêͳÉÁË»ùÓÚƪÕ¶à¼ÒÀ´æ½á¹
                                                                                              µÄ                                                                                                                                                       HIT-863¢òÐÍ×Ô¶¯ÎÄժϵ³¡£
                                                                                                                                                                                                                                                         ½üÁÄêÀ´£¬ÓÊÂÕâÏîÑо¿µ¥Î»²¶Ôö¼¡±©çó§Å¢¹¤³ÌÖÒåÚÉÃ
                                                                                              µÄÎÕª·½¨ÀàËÆÓÚ                                                                                                                                                                                                                                 Paice µÄÑ¡ÔñÓëÉú³ÎÕª·¨£¬¿Ç°Ö÷Ò¶¼ÆË㻲¾½ÃæÂ
                                                                                              [46]¡£É½Î÷´óѧ¹ù±þ×ÌÊÚÒ²Ô¿ªÕ¶¯ÄµÐ¾¬ËûÃÇӻͳ¼Æ·¨Öö
                                                                                              ½á¹ [47]¡£¾ÝϤ¬                                                                                                                                                                                                                           IBM ÖйúѾ¿ÄºÍ´ó½΢Èí«Ë¶¼ÔÚÆׯժµ²·¡£
                                                                                                                                                ×ÛÉÏËùÊö£¬Ô¶¯ÕªÂ¼ºÍÀí½âÎĸ÷Óг¤Ì¡Ü¹»ÃÚ·ÇÞòûµ±
                                                Ç°×ÔÈ»ÓïÑ´¦Àí¼ÊõÃæÏòÕµÁ£¬¯ÄÜ÷Æ«ÉÚËü¾Ö޶α²ã
                                                ½á¹µÄ·ÖÎö£¬ËùÒÔ¾-ýü                                                                                                                                                                                                                                                                                                                           40 Äêµ·¢Õ¹ÒѽÓü¼Êõ«ÏÞ£¬ÎªÖÁ¿ºÜÔÙÐɾ¡Àíâ
ÎÄÕªþÉüÁìÓò¿í¶È£¬»¡ËÀ½âî×÷ÂÛ̵¼ÖºÜ¸ß«ÊÃÐÔÏÍÚ
Ô¤¼ûµÄδÀÖÐÇ°¾-¡£ÅÏ¢³éÈܹ»Í¨ýرàÕª¿òÊÓ¦ÂÁì¬Ëü
ÎÄÕªÖÊÁ¿²¢»±ÈÀí½âÑ·É«£¬¶øÓç¸üË¡ùÚá¹µ×ԯ漰ìò
ʶ£¬ËùÒÔüºÍׯժ¼»ÑÇÃæÏò·ÜÞӵıÉÚýÈëÁƽá¹Ö
ÎÄÕªÖÊÁ¿ÓÐ˽ϴóµÌá¸ß¡£â·¨×Ûº§¹û¾ùÅÚÔ¶¯Â¼ÍÀí


                                                                                                                                                                                                                                            ²Î¿¼ ÄÏ×

                                                                                                                                                                                                                                                                    1 K.S.Jones and E-N Brigitte.Introduction:Automatic Summ-
                                                                                                                                                                                                                                            arizing.Information Processing & Management,1995,31(5):625¡« 630
                                                                                                                                                                                                                                                                    2 H.P.Luhn.The Automatic Creation of Literature Abstracts.IBM Journal of
                                                                                                                                                                                                                                            Research and Development,1958,2(2):159¡« 165
                                                                                                                                                                                                                                                                    3 ¹þÂÞµ¡¤²©¿Æ£¬é¶ûË      L¡¤±´Äá°£ºÏÖø¬ÀµÃ¯ÉúÍõª½òÒë¡ÎÕ¸ÅîÓ·
                                                                                                                                                                                                                                            ·¨¡£ÊéÄ¿ÎÏ׳ö°æÉç¬                          1991
                                                                                                                                                                                                                                                                    4 B.A.Mathis and J.E.Rush.Abstracting.Encyclopedia of Co-mputer and
                                                                                                                                                                                                                                                               Tehcnology,Vol.1,New York:Marcel Dekker Inc.,1975,102¡« 142
                                                                                                                                                                                                                                                                    5 L.B.Doyle.Indexing and Abstracting by Association.Amer-ican
                                                                                                                                                                                                                                            Documentation,October,1962,379¡« 390
                                                                                                                                                                                                                                                                    6 R.Brandow,K.Mitze and L.F.Rau.Automatic Condensation of Electronic
                                                                                                                                                                                                                                            Publications by Sentence Selection. Information P-rocessing &
                                                                                                                                                                                                                                            Management,1995,31(5):675¡« 685




                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        e ÏßͼÇ飨                                     http://www.chinalibs.net£©                2003-11-8
                         7 H.P.Edmundson and R.E.Wyllys:Automatic Abstracting andIndexing¡ª Survey
and Recommendations.Communications of the ACM,1961,4(5):226¡« 234
                         8 H.P.Edmundson.Automatic Abstracting,TRW Computer Divis-ion,Thompson Ram
Wooldridge,Inc.,Canoga Park,California:1963,AD406 155
                         9 H.P.Edmundson.Problems of automatic abstracting.Commun-ications of
ACM,1964,7(4):259¡« 263
                         10 H.P,Edmundson.New methods in automatic abstracting.Jo-urnal of the
Association for Computing Machinery,1969,16(2):264¡« 285
                         11 J.J.Pollock and A.Zamora.Automatic Abstracting Researchat Chemical
Abstracts Service.Journal of Chemical Informationand Comouter
Sciences,1975,15(4):226¡« 232
                         12 T.Nomoto and Yuji Matsumoto:Data Reliability and ItsEffects on
Automatic Abstracting.Proceedings of the Fifth Wor-kshop on Very Large
Corpora.August,1997,113¡« 126
                         13 B.A.Mathis,J.E.Rush and C.E.Young.Improvement of Auto-matic Abstracts
by the Use of Structural Analysis.Journal ofAmerican Society for Information
Science,1973,24(2):101¡« 109
                         14 Áõ¿ªçø£¬¹ù±þÑסÔÈ»Óï´¦ÀíƧ³ö°æÉ                1991
                         15 ÂíÏ£ÎĬÀîС±õìÔ½×È»ÓïÑ´¦ë¶¯ÕªÖÇܼʵͳù
                    1988,99¡« 117
                         16 L.F.Rau,P.S.Jacobs and Uri Zernik.Information Extract-ing and Text
                    Summarization Using Lingustic Knowledge Acquisti-on.Information Processing &
                    Management,1989,25(4):419¡« 428
                         17 P.S.Jacobs and L.F.Rau.Scisor:Extracting Informationfrom On-Line
News.Communication of the ACM,1990,33(11):88¡« 97
                         18 R.Kuhlen.Some Similarities and Differences between In-tellectual and
Macine Text Understanding for the Purpose of A-bstracting.Proceddings of the
Fifth International Research Fo-rum in Information Science(IRFIS
5),Heidelberg,F.R.G.,September5-7,1983,Edited by H.J.Dietschmann,Amsterdam,New
York:Oxford,Elsevier Science Publishers,1984,87¡« 109
                         19 Ò¦Ìì˳µÈ¡£×Ô»ÓïÑÀí½âªÖÃúÆ÷¶®àÄо¿Çå´ó§ö°æ
É磬¹ãÎ÷¿Æѧ¼Êõ³ö°æ                                                   1995
                         20 D.Fum,G.Guida and C.Tasso.Forward and Backward Reasoni-ng in Automatic
                    Abstracting.COLING 82,1982,83¡« 88
                         21 P.A.Jones and C.D.Paice.A 'Select and Generate' Approa-ch to Automatic
                    Abstracting.Proceedings of the 14th InformationRetrieval Colloquium,1993,141¡«
                    154
                         22 C.D.Paice.Constructing Literature Abstracts by Computer:Techniques and
                    Prospects.Information Processing & Management,1990,26(1):171¡« 186
                         23 W.J.Black.Knowledge-based abstracting.Online Review,1990,14(5):327¡«
                    340
                         24 G.Salton,J.Allan,C.Buckleym and Amit Singhal.AutomaticAnalysis,Theme
                    Genaration,and Summarization of Machine-
                    ReadableTexts.Science,1994,264(3):1421¡« 1426
                         25 G.Salton,J.Allan and A.Singhal.Automatic Text Decompo-sition and
                    Structuring.Information Processing & Management,1996,32(2):127¡« 138
                         26 G.Salton,A.Singhal,M.Mitra and C.Buckley.Automatic TextStructuring and
                    Summarization.Information Processing & Manage-ment,1997,33(2):193¡« 207
                         27 Seiji Miike,Etsuo Itoh,Kenji Ono and Kazuo Sumita.AFull-Text Retrieval
                    System with a Dynamic Abstract GenerationFunction.SIGIR Forum,1994,152¡« 161




                                                        e ÏßͼÇ飨   http://www.chinalibs.net£©   2003-11-8
                                                                                                       28 K.Ono,K.Sumita and S.Miike.Abstract Generation Based onRhetorical
                                                                                                  Structure Extraction.COLING 94,Kyoto,August 5¡« 9,1994,344¡« 348
                                                                                                       29 Jiri Janos.Results of an Experiment in Automatic Extr-acting and
                                                                                                  Problems in the Use of Condensed Form.Information
                                                                                                  andDocumentation,1978,3(1):13¡« 17
                                                                                                       30 Jiri Jaros.Theory of Functional Sentence Perspective and Its
                                                                                                  Application for the Purposes of Automatic Extracting.Inf-ormation Processing &
                                                                                                  Management,1979,15,19¡« 25
                                                                                                       31 T.Maeda,An Approach toward Functional Text StructureAnalysis of
                                                                                                  Scientific and Technical Documents.Information Pr-ocessing &
                                                                                                  Management,1981,17(6):329¡« 339
                                                                                                       32 Susan Bonzi and Elizabeth Liddy.The Use of AnaphoricResolution for
                                                                                                  Document Description in Information Retrieval.Information Processing &
                                                                                                  Management,1989,25(4):429¡« 441
                                                                                                       33 E.D.Liddy.Anaphora in Natural language Processing andInformation
                                                                                                  Retrieval.Information Processing & Management,1990,26(1):39¡« 52
                                                                                                       34 E.D.Liddy.The Discourse-Level Structure of Emprical A-bstracts:an
                                                                                                  Exploratory Strudy.Information Processing & Manag-ement,1991,27(1):55¡« 81
                                                                                                       35 Íõ±ø¡£ÃÀ¹ú»àÎÄÕª¸Å¿ö¬Çé¨Ñ§                                                                        1985,4(2):166¡« 171
                                                                                                       36 ÀîÃ÷¡£´Ó×ÖƵͳ¼ö·¢ÄÐÎÕªÔ¶¯±àÏúÊéǨõ¬
                                                                                                  1996,(3):42¡« 45
                                                                                                       37 ËÕº£¾¬ÍõÓÀ³É¡ÖÐÎĿƼÏתµÔ¶¯±à´Çé¨Ñ§                                                                                    1989,8(6):433¡«
                                                                                                  439
                                                                                                       38 ĪÑ࣬ÍõÓÀ³É¡ÖÐÎÏ×ÕÒµÔ¶¯±Æ´ú¼ÊéǨ                                                                                        1993,(3),10¡«
                                                           12
                                                                                                       39 ÍõÓÀ³É¡£ÖÐÎÄÅÏ¢´¦í¼Ê°Æä»ùº½¨óѧöæç¬                                                                                    1991
                                                                                                       40 ÍõÓÀ³É£¬Ðí»ÛÃô¡                                       OA ÖÐÎÄÏ×Ô¶¯ÕªÒµÍ³¡£Ç鱨ѧ¬                                   1997,16(2):128¡« 132
                                                                                                       41 Àî¿¡½Ü£·ÇÊÏÞÓòÖÐÎÄ×Ô¶¯ÕªµÍ³Ñ¾ë¹þû±õ¤Ò´ó§²©ÂÛ¬
1995
                                                                                                       42 ÐìÔ½£¬Àõ¶×¯ÎÄÕªµÑ¾¿ÓëʼùÚÒ»çÈ˹¤ÖÇÜÁºÏ§áéÂÛ
¼¯£¬                                                                                                  1990,346¡« 350
                                                                                                       43 ÀîС±õ£¬ìԽ׶¯ÎÄժϵͳ                                                            EAAS¡£Èí¼þѧ±¨¬         1991,(4),12¡« 18
                                                                                                       44 Íõ½¨²¡£ÃæÏòÒéÂÛÎÄÀíâµ×Ô¶¯Õª³Ñо¿ÓëÌÖ¹þû±¤´ó§©Ê
     뀣                                                                                             1992
                                                                                                       45 Áõͦ£¬ÎâÑÒ¿ªÖý¡»ùÓÚÐÅÏ¢³éȺı¾Éúµ×Ô¶¯Õè¼ÆǨ§
          ±¨£¬                                                                                        1997,16£¨Ôö¿¯£©                                    :24¡« 29
                                                                                                       46 ÑîÏþÀ¼£¬Ëη«ÖÓÒåÐÅ¡»ùÚÔñÉú³ÄÕª¨µ×¶¯Í¾¿ëÊȹ
               µÚËĽì¼ÆãÓïÑÔ§ÁªºÏÊõ»áÒéÂÛί£¬±¾©Çå´ó³ö°æÉç                                                                                                                                                                  1997,313¡« 318
                                                                                                       47 Ѧ´ä·¼£¬ÀîÏþè¹ù±ûסºÓïÎÄÕªµÍ³Öо½áÔ¶¯öÈ«úÚËìÆ
                                                           ËãÓïÑÔ§ÁªºÏÊõ»áÒéÂÛÎļ¯£¬±¾©Çå´ó³ö°æÉç                                                                                                                  1997,338¡« 344

[×÷Õß¼ò½é                  ] Áõͦ£¬                 1973 ÄêÉú£¬²©Ê¿ÑоÖ÷Òª´ÓÂÎ×Ô¶¯Õ¡¢µÈ·½
ÃæµÄÑо¿¡£ÍõªÖý¬                                     1933 ÄêÉú£¬½ÌÊÚ³¤Æ´ÓÂ×ÔÈ»ïÑÀíâ¡¢ÖÐÎÅϦµ¾¿




                                                                                                                                           e ÏßͼÇ飨               http://www.chinalibs.net£©                                2003-11-8

				
DOCUMENT INFO
Shared By:
Stats:
views:69
posted:3/19/2010
language:English
pages:9
Description: 自动文摘技术 方法 探讨 自动文本摘要方法