The interface between model-theoretic and corpus-based semantics - PowerPoint PPT Presentation

Loading...

PPT – The interface between model-theoretic and corpus-based semantics PowerPoint presentation | free to download - id: 76e94c-YTc4Y



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

The interface between model-theoretic and corpus-based semantics

Description:

Title: Die Schnittstelle zwischen formaler und korpusbasierter Semantik Author: Sebastian Pado Last modified by: Sabine Mohr Created Date: 11/25/2008 1:17:40 AM – PowerPoint PPT presentation

Number of Views:29
Avg rating:3.0/5.0
Slides: 17
Provided by: Sebas54
Learn more at: http://www.uni-stuttgart.de
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: The interface between model-theoretic and corpus-based semantics


1
The interface between model-theoretic and
corpus-based semantics
  • Sebastian Pado

2
Natural language semantics
  • Model-theoretic semantics
  • Compositional calculation of sentence meaning
  • Formal descriptions of ambiguities
  • Inference
  • Corpus-based semantics
  • Distributional, graded meaning representation
  • Probabilistic knowledge acquisition from corpora
  • Prediction of linguistic behaviour based on
    context

3
Complementary benefits
  • Model-theoretic
  • semantics
  • Good for sentence level
  • (closed word classes)
  • Limited coverage
  • Correct

Corpus-based semantics Good for lexical
level (open word classes) High coverage,
robustness Approximative
  • How to divide work between the approaches?

4
Strategies
  • More expressive representations for corpus-based
    models of meaning Compositionality in vector
    spaces
  • Ongoing collaboration with Katrin Erk (Dept. of
    Linguistics, U. Texas at Austin)
  • Corpus-based methods for enrichment of formal
    meaning representations
  • Core of SFB project proposal

5
Strategy 1
  • More expressive representations for corpus-based
    models of meaning

6
Compositionality in Vector Spaces
  • Vector space Representation of word meaning by
    context co-occurrences
  • What is the representation of a phrase?
  • Centroid of two vectors?
  • No Must take mode of combination into account
  • a horse draws pull
  • draw a horse sketch

7
A first step
  • Structured vector space model Erk Pado 2008
  • Covers VerbObject, VerbSubject combinations
  • Word meaning consists of lexical vector plus
    selectional preferences (experiences) for
    dependents/governors

8
A first step
  • Structured vector space model Erk Pado 2008
  • Covers VerbObject, VerbSubject combinations
  • Phrase meaning consists of two vectors
  • Verb meaning modified by nominal expectations
    about governor
  • Noun meaning modified by verbal expectations
    about dependent

9
Current state
  • Evaluation Better distinction between
    contextually appropriate and inappropriate
    paraphrases (WSD-style task)
  • Further research questions
  • Generalisation to longer phrases
  • More expressive model of expectations
  • Modelling of phrases involving closed word
    classes
  • E.g. Negation

10
Strategy 2
  • Corpus-based methods for enrichment of formal
    meaning representations

11
Formal models of meaning in context
  • Lexicon entries cannot provide the full range of
    readings for words/phrases
  • Readings often productively negotiated in text
  • Type/sort conflict
  • Examples
  • Metonymy/Metaphor
  • Telic adjectives (fast typist)
  • Coercion/Reinterpretation

12
Example Coercion
  • Wegen einer 15-jährigen kam es zu einem Streit,
    in dessen Verlauf sie verletzt wurde.
  • Sie hatte sich mit einem 21-jährigen
    unterhalten.
  • Red and blue expressions are coreferring, but red
    expression has wrong type (wegen takes lte,tgt
    expression is ltegt).
  • Here, context overtly provides missing event
  • Often, this is not the case Operator must be
    recovered from general knowledge

13
The role of corpus methods
  • Acquisition of general reinterpretation operators
    from corpora
  • Recovery/prediction of operators for instances
    with type/sort conflict
  • Making implicit meaning explicit can be seen as
    context-driven semantic specification
  • Interest primarily empirical

14
Project Steps
  • Creation of multilingual corpus of type/sort
    conflict cases with human annotations
  • Informed by formal considerations
  • Development of CL methods to predict operators
    for conflict resolution
  • Ideally, task-based evaluation (to be determined)
  • Consequences/insights for formal descriptions

15
Research Questions
  • When can operators be found overtly in context
    when must general operators be recovered?
  • Influence of local discourse?
  • CL methods for efficient and accurate prediction
    of operators
  • What linguistic levels are helpful? Semantic
    classes, semantic roles, dependency relations, ?
  • Focus on more than one language Can bilingual
    processing help?
  • What is the level of generality of acquired
    operators?
  • What shape do peoples expectations have?
  • Do peoples judgments of recovered operators
    agree?
  • Can empirical results have impact on formal
    descriptions?
  • E.g. do sort and type conflicts behave
    differently or similarly?
  • Relation to work on textual entailment?

16
Collaborations
  • D1 (Representation of ambiguities)
  • Formal descriptions as information source for
    corpus development
  • Attempt to transfer of empirical results back
    into theory
  • B5 (Polysemy in a conceptual system)
  • Ontological information as knowledge source for
    CL operator models
  • Entailment as shared evaluation task
  • Open for other ideas
About PowerShow.com