Collecting Weighted Coercions from Crowd-Sourced Lexical Data for Compositional Semantic Analysis

Lafourcade, Mathieu; Mery, Bruno; Mirzapour, Mehdi; Moot, Richard; Retoré, Christian

doi:10.1007/978-3-319-93794-6_15

Search citation statements

Order By: Relevance

Paper Sections

Select...

Conclusion and Possible Extensions1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

Publication Types

Select...

Book2

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other task is measuring semantic gradience in natural language. Some line of research suggests this feature within lexical/compositional frameworks by creating and enrichment of the wide-coverage weighted lexical resources from crowd-sourced data [18].…”

Section: Conclusion and Possible Extensionsmentioning

confidence: 99%

Measuring Linguistic Complexity: Introducing a New Categorial Metric

Mirzapour

Prost

Retoré

2019

Studies in Computational Intelligence

Self Cite

View full text Add to dashboard Cite

This paper provides a computable quantitative measure which accounts for the difficulty in human processing of sentences: why is a sentence harder to parse than another one? Why is some reading of a sentence easier than another one? We take for granted psycholinguistic results on human processing complexity like the ones by Gibson. We define a new metric which uses Categorial Proof Nets to correctly model Gibson's account in his Dependency Locality Theory. The proposed metric correctly predicts some performance phenomena such as structures with embedded pronouns, garden paths, unacceptable center embeddings, preference for lower attachment and passive paraphrases acceptability. Our proposal gets closer to the modern computational psycholinguistic theories, while it opens the door to include semantic complexity, because of the straightforward syntax-semantics interface in categorial grammars.

show abstract

Section: Conclusion and Possible Extensionsmentioning

confidence: 99%