SProUT
Shallow Processing with Unification
and Typed Feature Structures
Jakub Piskorski
Language Technology Lab
DFKI GmbH
Jakub Piskorski Warszawa, 6.10 .2003
Information Extraction
Munich, February 18, 1997, Siemens AG and The General Electric Company (GEC),
London, have merged their UK private communication systems and networks
activities to form a new company, Siemens GEC Communication Systems Limited.
Munich, February 18, 1997, Siemens AG and The General Electric Company (GEC),
London, have merged their UK private communication systems and networks
activities to form a new company, Siemens GEC Communication Systems Limited.
JOINT-VENTURE FOUNDATION EVENT
VENTURE: Siemens GEC Communication Systems Limited
PARTNERS: Siemens AG, The General Electric
TIME: February 18 1997
PRODUCT/SERVICE: communication systems, networks activities
LOCATION: Munich
Jakub Piskorski Warszawa, 6.10 .2003
Finite-State based approaches
SPPC - pure finite-state based STP, small number of basic predicates
SMES – predciates inspect arbitrary properties of the input tokens/fragments
FASTUS – uses CPSL (Common Pattern Specification Language)
GATE – uses JAPE (Java Annotation Patterns Engine)
Jakub Piskorski Warszawa, 6.10 .2003
Motivation for SProUT
One System for Multilingual and Domain Adaptive Shallow Text Processing
Trade-off between efficiency and expressiveness
Modularity
Flexible integration of different processing modules
Portability
Industrial standards
Jakub Piskorski Warszawa, 6.10 .2003
Credits
SProUT is a joint work by:
Witold Drożdżyński,
Ulrich Krieger,
Jakub Piskorski,
Ulrich Schäfer,
Feiyu Xu
Jakub Piskorski Warszawa, 6.10 .2003
SProUT Architecture
LINGUISTIC
INPUT DATA PROCESSING LEXICAL
RESOURCES RESOURCES
JTFS
STREAM OF
TEXT ITEMS
…. [..] [..] [..] ….
XTDL REGULAR EXTENDED XTDL
GRAMMAR OPTIMIZED STRUCTURED
COMPILER INTERPRETER
FINITE-STATE OUTPUT DATA
NETWORK
FINITE-STATE
MACHINE
TOOLKIT
GRAMMAR DEVELOPMENT ONLINE PROCESSING
ENVIRONMENT
Jakub Piskorski Warszawa, 6.10 .2003
Core Components – FSM Toolkit
Finite-state Machine Toolkit for building, combining,
and optimizing finite-state devices
Finite-state Machine model: FSA, WFSA, FST, WFST
Arbitrary real-valued semirings
Some new crucial STP-relevant operations
(e.g., incremental construction of minimal deterministic FSAs)
Various memory models
Functionality similar to AT&T tools
Jakub Piskorski Warszawa, 6.10 .2003
Core Components – Regular Compiler
Definition and configuration via XML
Unicode compatible
Extendible set of circa 20 operations
Scanner definitions vs. general regular expressions
Biasing optimization process
Various ways of handling ambiguities
Direct database connection for flexible pattern-based transformation of
linguistic resources into optimized FS representation
Regular expressions over TFSs (SProUT) with restrictions
Jakub Piskorski Warszawa, 6.10 .2003
Core Components – Typed Feature Structure Package
JAVA implementation of TFSs
Efficient unification operations
Dynamic extension of the type hierarchy
Other operations: subsumptipon checking, deep copying, path selection,
feature iteration, and various printers
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Formalism
Combines typed feature structures (TFS) and regular expressions, including
coreferences and functional application
XTDL grammar rules – production part on LHS, and output description on RHS
TDL used for establishment of a type hierarchy of linguistic entities
*top*
morph := sign & [POS atom,
atom *avm* *rule*
STEM atom,
INFL infl] tense sign infl index-avm
present token morph lang tokentype
de en separator url
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Formalism
Couple of standard regular operators:
concatenation optionality ?
disjunction | Kleene star *
Kleene plus + n-fold repetition {n}
m-n span repetition {m,n}
Unidirectional coreference under Kleene star (and restricted iteration)
[POS Det, ...] ([POS Adj, ..., RELN %LIST])* [POS Noun, ...] -> [..., RELN %LIST]
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Formalism
loc-pp :>
morph & [POS Prep & #preposition,
INFL [CASE #1, NUMBER #2, GENDER #3]]
morph & [POS Determiner,
INFL [CASE #1, NUMBER #2, GENDER #3]] ?
morph & [POS Adjective,
INFL [CASE #1, NUMBER #2, GENDER #3]] *
gazetteer & [TYPE general-location,
SURFACE #location]
-> [CAT location-pp,
PREP #preposition
LOCATION #location].
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Interpreter
1. Matching of regular patterns using unifiability (LHS)
2. LHS Pattern instance creation
3. Unfication of the rule instance and matched input
Longest match strategy
Ambiguities allowed
Interpreter generates TFSs as output (cascaded architecture)
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Interpreter
Matched input sequence “im sonnigen Rom” (in sunny Rome)
SURFACE im SURFACE sonnigen
STEM STEM
im sonnig
POS POS
IN
Prep Adjective SURFACE Rom
, ,
CASE nom CASE case gazetteer TYPE
general - location
INFL NUMBER plural INFL NUMBER number
GENDER fem morph GENDER gender
morph infl infl
rule
Jakub Piskorski Warszawa, 6.10 .2003
XTDL Interpreter
Rule with an instantiated pattern on the LHS
POS 5 Prep POS Adjective
CASE 1
CASE 1
SURFACE 4
IN NUMBER 2 , NUMBER 2 ,
INFL
INFL
gazetteer TYPE general - location
GENDER 3
infl morph GENDER 3
infl
morph
CAT location - np
OUT PREP 5
LOCATION 4
phrase
rule
Jakub Piskorski Warszawa, 6.10 .2003
XTDL formalism
Unified result
SURFACE im SURFACE sonnigen
STEM STEM
im sonnig
5 Prep
IN
POS POS Adjective SURFACE 4 Rom
, ,
CASE 1 dat CASE 1 gazetteer TYPE
general - location
INFL NUMBER 2 sing INFL NUMBER 2
GENDER 3 neut
infl morph GENDER 3
infl
morph
CAT location - np
OUT PREP 5
LOCATION
phrase
4
rule
Jakub Piskorski Warszawa, 6.10 .2003
Linguistic Processing Resources
Tokenization
Gazetteer
Extended Gazetteer
Morphology
Sentence Splitter
Reference Matcher
Jakub Piskorski Warszawa, 6.10 .2003
Tokenization
Text segmentation into tokens
Fine-grained token classification (ca. 30 types)
complex_compound_first_capital : AT&T-Chief
Token postsegmentation
‘’ ‘’
Token Subclassification
Information
START : 25
END : 34
contains_position_sufix: AT&T-Chief MAIN : first _ capital
LANG : german LANG : english
SUB : DOM : any , DOM : any
SPEC : has _ noun _ ending SPEC : has_noun_ending
Jakub Piskorski Warszawa, 6.10 .2003
Gazetteer/Extended Gazetteer
for storing static named-entities (eg. locations) or keywords (eg. company|
designators, month names, etc.)
Extended Gazetteer allows for associating entries with a list of arbitrary
attribute-value pairs (and uses path compression)
...
Warsaw | gaz_type:city | concept:Warsaw
Warszawa | gaz_type:city | concept:Warsaw
Varsovie | gaz_type:city | concept:Warsaw
...
Case Sensitivie/Insensitive Modus
Unicode compatibility
Jakub Piskorski Warszawa, 6.10 .2003
Morphology
compactification of available full-form lexica
external components implemented as server
Full-form lexica obtained from ‘compactified’ MMORPH:
English 200,000 entries
German 830,000 entries + Shallow Compound Recognition
French 225,000 entries
Spanish 570,000 entries
Italian 330,000 entries
Dutch ? Entries (under development)
Asian Languages:
Chinese – Shanxi
Japanese – Chasen
Other:
Czech – 600,000 entries + HMM-based Part-of-Speech Tagging
Polish – 120,000 lexemes (Morfeusz)
Lithuanian – Lemouklis
Russian – under acquisition
Jakub Piskorski Warszawa, 6.10 .2003
Morphology
Compound Recognition & Segmentation for German
“Biergartenfest” “Wein“ + “sorten“ (wine types)
[Bier [garten fest]] vs. [[Bier garten] fest] “Wein” + “s“ + “orten“ (wine places)
(„Autoradiozubehör“ – radio car equipment)
Autoradiozubehör Autoradiozubehör
Autoradiozubehör Autoradiozubehör
Autoradiozubehör Autoradiozubehör
Next: Adoptation for processing Dutch compounds
Jakub Piskorski Warszawa, 6.10 .2003
System Description Language
Construction of a concrete system instance via definition of a
regular expression of module specifications
M1 M 2 output of M 1 serves as the input to M 2
M* fixpoint computation
M1 M 2 quasi - parallel computation of independent modules
All lingusitic modules must implement a specific JAVA interface
Automatic compilation of system description into a single JAVA class
Jakub Piskorski Warszawa, 6.10 .2003
System Description Language
(M1 M2)(input)
M1.clearState();
M1.setInput(input);
M1.setOutput(M1.computeOutput(M1.getInput()));
M2.clearState();
M2.setInput(mediateSeq(M1,M2));
M2.setOutput(M2.computeOutput(M2.getInput()));
return M2.getOutput();
(M*)(input)
M.clearState();
M.setInput(input);
M.setOutput(mediateFix(M));
return M.getOutput();
Jakub Piskorski Warszawa, 6.10 .2003
Optimization of Grammar processing
Problem: TFSs treated as symbolic values by FSM Toolkit
Sorting outgoing transitions from slected states
(transition hierarchy under subsumption)
- flat trees for bad-style grammars
Extending transition hierarchy via additional nodes
[ TOP ]
[TOKEN]
[MORPH stem: „Prof.‟] [GAZETTEER type: X]
Jakub Piskorski Warszawa, 6.10 .2003
Optimization of Grammar processing
Input text consisting of 32 520 words, 157 080 characters, 22 pages
+ English Grammar for NE (circa 700 transitions from the initial state)
Run-time behaviour with Tokenizer/Gazetter/Morphology:
before: overall: 17.7 seconds candidate pattern selection: 11.6
now: overall: 13.2 seconds candidate pattern selection: 6.9
Jakub Piskorski Warszawa, 6.10 .2003
Optimization of Grammar processing
Using restrictions during compilation of XTDL grammars into FS-format
‟Determinization under subsumption‟ -> Approximation
‟Expansion‟ techniques for highly recursive grammars
Jakub Piskorski Warszawa, 6.10 .2003
Adapting SProUT to processing Polish
Tokenization – trivial
Morphology – integration of Morfeusz (Marcin Woliński)
Part-of-speech Disambiguation - ?
Gazetteer - several strategies:
- list all inflectional variants with additional morphological information
- interplay between gazetteer and morphology
- component for guessing morphological information of unknown words
Grammar Adaptation
- provide additional information to control inflection by using
STEM attribute instead of SURFACE
Jakub Piskorski Warszawa, 6.10 .2003
Future Work
Further work concerning optimization of grammar processing
Various search strategies
Additional linguistic processing resources
Adopting to processing new languages
Real data testing: large grammars and real-world texts
Utilization in research and industrial projects
Jakub Piskorski Warszawa, 6.10 .2003
Examples – Simple grammar for person names
;; dummy rule for title
title :/ gazetteer & [SURFACE #title, GTYPE gaz_title] -> #title.
;; dummy rule for position
position :/ gazetteer & [SURFACE #position, GTYPE gaz_position] -> #position.
;; dummy rule for complex position, zB. Dierktor und CEO
complex_position :/
(gazetteer & [GTYPE gaz_position, SURFACE #pos1]
token & [SURFACE "und"]
gazetteer & [GTYPE gaz_position, SURFACE #pos2])
-> #position, where #position = Append(#pos1," ","und"," ",#pos2).
Jakub Piskorski Warszawa, 6.10 .2003
Examples – Simple grammar for person names
;; dummy rule for given name
given_name :/ gazetteer & [SURFACE #name, GTYPE gaz_given_name] -> #name.
;; dummy rule for name-suffix such as "Jr."
name_suffix :/
(token & [ SURFACE ","] ?)
token & [ SURFACE "Jr" & #suffix ] | token & [ SURFACE "jr" & #suffix ]
(token & [ SURFACE "." ] ?)
-> #suffix.
;; dummy rule for initial "M." and middle name
initial :/
(gazetteer & [GTYPE gaz_initial, SURFACE #initial]
token & [SURFACE "."] ?)
-> #middle, where #middle = Append(#initial, ".").
Jakub Piskorski Warszawa, 6.10 .2003
Examples – Simple grammar for person names
;; dummy rule for infix like "van", "van der"
infix :/ gazetteer & [GTYPE gaz_name_infix, SURFACE #infix] -> #infix.
;; dummy rule for last name
last_name :/
token & [TYPE first_capital_word, SURFACE #name]
| token & [TYPE mixed_word_first_capital, SURFACE #name]
| token & [TYPE word_with_hyphen_first_capital, SURFACE #name]
| token & [TYPE word_with_apostrophee_first_capital, SURFACE #name]
-> #name.
;; dummy rule for last name with infix
last_name_with_infix :/
@seek(infix) & #infix
@seek(last_name) & #last_name
-> #last, where #last=Append(#infix," ",#last_name).
Jakub Piskorski Warszawa, 6.10 .2003
Examples – Simple grammar for person names
;; rule for person names, example: Direktor und CTO Prof. Dr. hab. Witold P. van der Berg, Jr.
person :>
((@seek(position) & #pos | @seek(complex_position) & #pos) token & [TYPE comma] ?)?
@seek(title) & #title ?
(@seek(given_name) & #given_name (@seek(given_name) & #given_name_extra ?)
| (@seek(initial) & #given_name))
@seek(initial) & #middle1 ?
@seek(initial) & #middle2 ?
(@seek(last_name) & #last_name | @seek(last_name_with_infix) & #last_name)
@seek(name_suffix) & #suffix ?
-> ne-person & [GIVEN_NAME #first_name,
TITLE #title,
SURNAME #last_name,
P-POSITION #position,
NAME-SUFFIX #suffix],
where #first_name = ConcWithBlanks(#given_name,#given_name_extra,#middle1,#middle2).
Jakub Piskorski Warszawa, 6.10 .2003
Examples – Embedding rules
simple_noun_phrase :> .................
-> phrase & [CAT np,
SURFACE #info,
AGR [N #n,
C #c,
G #g]], where #info=..........
simple_event :> @seek(person) & #person
morph & [POS verb, STEM #action]
@seek(simple_noun_phrase) & [SURFACE #info]
-> [PERSON #person, ACTION #action, OBJECT #info].
Jakub Piskorski Warszawa, 6.10 .2003