Lexical Substitution for Evaluating Compositional Distributional Models
Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space. They have been predominantly evaluated on limited, artificial tasks such as semantic sentence similarity on hand-constructed datasets. This paper argues for lexical substitution (LexSub) as a means to evaluate CDSMs. LexSub is a more natural task, enables us to evaluate meaning composition at the level of individual words, and provides a common ground to compare CDSMs with dedicated LexSub models. We create a LexSub dataset for CDSM evaluation from a corpus with manual {``}all-words{''} LexSub annotation. Our experiments indicate that the Practical Lexical Function CDSM outperforms simple component-wise CDSMs and performs on par with the context2vec LexSub model using the same context.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language InferenceSentenceSentence SimilaritySentiment AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Presentation of the SemDis 2014 workshop: distributional semantics for two tasks - lexical substitution and exploration of specialized corpora (Pr\'esentation de l'atelier SemDis 2014 : s\'emantique distributionnelle pour la substitution lexicale et l'exploration de corpus sp\'ecialis\'es) [in French]
Fusion of Compositional Network-based and Lexical Function Distributional Semantic Models
Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics
Lexical Variability and Compositionality: Investigating Idiomaticity with Distributional Semantic Models
Typology of Adjectives Benchmark for Compositional Distributional Models
In this paper we present a novel application of compositional distributional semantic models (CDSMs): prediction of lexical typology. The paper introduces the notion of typological closeness, which is a novel rigorous fo…
Semantic SimilaritySemantic Textual Similarity