Docstoc

Acquisition of Semantic Classes for Adjectives from Distributional - PowerPoint - PowerPoint

Document Sample
Acquisition of Semantic Classes for Adjectives from Distributional - PowerPoint - PowerPoint Powered By Docstoc
					Acquisition of Semantic Classes
     for Adjectives from
   Distributional Evidence
          Gemma Boleda
      Universitat Pompeu Fabra
             Barcelona
              general picture
• automatic classification of adjectives
  – Catalan
• according to broad semantic characteristics
• clustering
  – syntactic evidence
                  motivation
• Lexical Acquisition
  – infer properties of words
  – lexical bottleneck
     • both symbolic and statistical approaches
• adjectives
  – determining NP reference
     • the French general
  – establishing properties of entities
     • this maimai is round and sweet
                    motivation
• initial motivation: POS-tagging
   – 55% remaining ambiguity involves adjectives
     general francès: „French general‟ or „general French‟?
• observations
   – general tendencies in syntactic behaviour of adjectives
   – ... which correspond to broad semantic properties
• generalisation: best at semantic level
   – low-level tasks (POS-tagging)
   – initial schema for lexical semantic representation
                      approach
• no general, well established semantic classification
   – have to build and test ours!
• clustering: unsupervised technique
   – groups objects according to feature distribution
   – does not depend on pre-classification
                        rodó nature of
   – provides insight into the„round‟ the data0.4 0.4   0.2
• shallow approach to syntax: n-grams 0.5
                   dolç „sweet‟                  0.4 0.1
   – limited syntactic distribution
                        francès „French‟
   – local relationship to arguments       0.1   0.6 0.3
   => test feasibility
                       italià „Italian‟    0.05 0.5 0.45
                      outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
                           Boleda, Badia, Batlle (2004)
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
            adjective syntax
• default function: noun modifier (92%)
  – right of the noun (default position: 72%)
  – some to the left („epithets‟: 28%)
• predicative uses unfrequent (7%), but
  significant
         two-way classification
• number of arguments
   – unary: pilota vermella „red ball‟
   – binary: professor gelós de la Maria „teacher jealous of
     Maria‟
• ontological kind (Ontological Semantics)
   – basic: vermell ‘red’
   – object: malaltia pulmonar „pulmonary disease‟ (=>
     lung)
   – event: propietat constitutiva „constitutive property‟ (=>
     constitutes)
       Ontological Semantics
• coverage (ordinary cases)
• machine tractability
• explicit model of world: ontology
  – vermell => attribute::colour::red(x)
  – pulmonar => related-to::lung(x)
  – constitutiu => event::benef::constitute(x)
• however: no commitment to particular
  framework
                 rationale
• observation: syntactic preferences
  correspond to semantic properties

• hypothesis: we can use syntactic features to
  infer semantic classes
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   conclusions and future work
           data and procedure
• 2283 adjectives
  >50 times in 16 million word Catalan corpus
     • lemma and morphological info
• cluster the whole set
  – perform different tasks on different subsets
     • tuning subset: choose features
     • Gold Standard: evaluation and analysis
    features and feature selection
•    features:
    –   empirically chosen from blind distribution
    –   double bigram, simplified POS-representation
ella diu que la         pilota vermella és     seva
she says that the       ball    red     is     hers
            -3ey -2dd -1cn              +1ve
• tuning subset: 100 adjectives
    – choose features (distribution)
Fig. A: Feature selection
                    analysis
•   Gold Standard
    –   80 adjectives
    –   annotated by 3 human judges, acceptable
        agreement (92 and 84%, .72 and .74 kappa)
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
   experiment 1: unary / binary
• final evaluation:10 features, raw percentage
  – clustering algorithm: k-means (cosine)


• predictions:
  – binary adjectives cooccur with prepositions
    more frequently than unary ones
  – unary adjectives are more flexible
            unary / binary: results
            unary (yellow)          • agreement with Gold
                                      Standard:
                    binary (red)       – 97%, kappa = 0.87
                                       – comparable to humans
                                    • features:
                                      cl      high   low
                                      0 (un) -1cn    +1prep

Fig. B: Clusters vs. unary/binary     1 (bin) +1prep (-1cn)
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
experiment 2: basic / object / event
• final evaluation: 32 features, normalisation
  – clustering algorithm: k-means (cosine)
• predictions:
  – basic adjectives are flexible, work as epithets,
    occur in predicative contexts, appear further
    from the noun
  – object adjectives appear rigidly after the noun
  – event adjectives tend to occur in predicative
    positions and do not act as epithets
       basic / object / event: results
      object (yellow)
                                   • agreement with Gold
               event (orange)        Standard:
                                         – 73%, kappa = 0.56
                                         – lower than humans
                                   • features:
                                         cl      high     low
                                         0 (obj) -1cn  -1ve
                                         1 (ev) +1prep
   basic (red)                           2 (bas) -1co  +1aj
Fig C: Clusters vs. basic/event/object
basic/object/event: error analysis
• something has gone wrong!
  – characterisation of event adjectives
            basic adjectives with an
                   unary event adjectivesbinary!
            object reading (polysemy)

                       binary event adjectives



 Fig C: Clusters vs.           Fig D: Clusters
 basic/event/object            vs. unary/binary
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
           partial conclusions
• overall, results seem to back up:
  – use of syntax-semantics interface for adjectives
  – linguistic predictions as to relevant features and
    differences across classes
  – shallow approach
• unary / binary: piece of cake
  – few binary adjectives, but worth spotting
    (denote relationships)
          partial conclusions
• basic / object / event: need reworking
  – object adjectives seem to be the most robust
    class
  – variation in basic adjectives (default class),
    polysemy
  – event adjectives: seem to behave much like
    basic adjectives with respect to features chosen
    => redefine class?
                    outline
•   adjective syntax and semantic classification
•   methodology
•   experiment 1
•   experiment 2
•   partial conclusions
•   outlook: rest of the thesis
     outlook: rest of the thesis
• rethink classification
• redefine features in light of results
• integrate polysemy judgments into the
  experiment and analysis
• perform experiments with other corpora
               classification
• what to do with event adjectives? cp.:
  – constitutiu „constitutive‟ (“active”)
  – legible „readable‟ (“passive”)
  – reproductor „reproducing‟ (“active,
    habituality”)
• yet another parameter: gradability
  – important for adjectives
  – should be easy to induce
        better blind distribution or self-
                defined features?
• n-grams: sparseness, selection
           empirical      accurate sparseness objective
blind                    X         X           ?

self       X?                                 X
           (depends on
           method)

• other features?
       – account for different levels of description
                  polysemy
• crucial aspect, explains much of results
• difficult to integrate!
  – meaningless kappa values
• alternatives?
  – clearer definition of polysemy within task
  – specific tests
  – other resources: dictionary?
             other resources
• CUCWeb (208 million word)
  http://www.catedratelefonica.upf.es
• test whether “more data is better data”
  (Mercer and Church 1993: 18-19)
   – advantages and challenges of Web corpora
• current results: for verb subcategorisation
  experiment, results 12 points lower than
  using smaller, balanced, controled corpus
Acquisition of Semantic Classes
     for Adjectives from
   Distributional Evidence
          Gemma Boleda
      Universitat Pompeu Fabra
             Barcelona

				
DOCUMENT INFO