paper-with-me

Papers

Lexical Substitution for Evaluating Compositional Distributional Models

2018-06-01 · NAACL 2018 6 · Maja Buljan, Sebastian Pad{\'o}, Jan {\v{S}}najder

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language InferenceSentenceSentence SimilaritySentiment Analysis

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
context2vec context2vec is an unsupervised model for learning generic context embedding of wide sentential contexts, using a bidirectional LSTM.…

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]

2014-07-01 · JEPTALNRECITAL 2014 7 · C{\'e}cile Fabre, Nabil Hathout, Lydia-Mai Ho-Dac, Fran{\c{c}}ois Morlane-Hond{\`e}re 외

Fusion of Compositional Network-based and Lexical Function Distributional Semantic Models

2015-06-01 · WS 2015 6 · Spiros Georgiladakis, Elias Iosif, Alex Potamianos, ros
Natural Language InferenceSemantic CompositionSemantic Textual Similarity

Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics

2015-06-01 · SEMEVAL 2015 6 · Abhijeet Gupta, Jason Utt, Sebastian Pad{\'o}
Machine TranslationSentiment Analysis

Lexical Variability and Compositionality: Investigating Idiomaticity with Distributional Semantic Models

2016-08-01 · WS 2016 8 · Marco Silvio Giuseppe Senaldi, Gianluca E. Lebani, Aless Lenci, ro

Typology of Adjectives Benchmark for Compositional Distributional Models

2016-05-01 · LREC 2016 5 · Daria Ryzhova, Maria Kyuseva, Denis Paperno

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