When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs

This paper analyzes the concept of opposition and describes a fully unsupervised method for its automatic discrimination from near-synonymy in Distributional Semantic Models (DSMs). The discriminating method is based on the hypothesis that, even though both near-synonyms and opposites are mostly dis...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Enrico Santus, Qin Lu, Alessandro Lenci, Chu-Ren Huang
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2015
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/3db40347814b4e6fa403e75647f18eed
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3db40347814b4e6fa403e75647f18eed
record_format	dspace
spelling	oai:doaj.org-article:3db40347814b4e6fa403e75647f18eed2021-12-02T09:52:33ZWhen Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs2499-455310.4000/ijcol.311https://doaj.org/article/3db40347814b4e6fa403e75647f18eed2015-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/311https://doaj.org/toc/2499-4553This paper analyzes the concept of opposition and describes a fully unsupervised method for its automatic discrimination from near-synonymy in Distributional Semantic Models (DSMs). The discriminating method is based on the hypothesis that, even though both near-synonyms and opposites are mostly distributionally similar, opposites are different from each other in at least one dimension of meaning, which can be assumed to be salient. Such hypothesis has been implemented in APAnt, a distributional measure that evaluates the extent of the intersection among the most relevant contexts of two words (where relevance is measured as mutual dependency), and its saliency (i.e. their average rank in the mutual dependency sorted list of contexts). The measure – previously introduced in some pilot studies – is presented here with two variants. Evaluation shows that it outperforms three baselines in an antonym retrieval task: the vector cosine, a baseline implementing the co-occurrence hypothesis, and a random rank. This paper describes the algorithm in details and analyzes its current limitations, suggesting that extensions may be developed for discriminating antonyms not only from near-synonyms but also from other semantic relations. During the evaluation, we have noticed that APAnt also has a particular preference for hypernyms.Enrico SantusQin LuAlessandro LenciChu-Ren HuangAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 1, Iss 1, Pp 47-60 (2015)
institution	DOAJ
collection	DOAJ
language	EN
topic	Social Sciences H Computational linguistics. Natural language processing P98-98.5
spellingShingle	Social Sciences H Computational linguistics. Natural language processing P98-98.5 Enrico Santus Qin Lu Alessandro Lenci Chu-Ren Huang When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
description	This paper analyzes the concept of opposition and describes a fully unsupervised method for its automatic discrimination from near-synonymy in Distributional Semantic Models (DSMs). The discriminating method is based on the hypothesis that, even though both near-synonyms and opposites are mostly distributionally similar, opposites are different from each other in at least one dimension of meaning, which can be assumed to be salient. Such hypothesis has been implemented in APAnt, a distributional measure that evaluates the extent of the intersection among the most relevant contexts of two words (where relevance is measured as mutual dependency), and its saliency (i.e. their average rank in the mutual dependency sorted list of contexts). The measure – previously introduced in some pilot studies – is presented here with two variants. Evaluation shows that it outperforms three baselines in an antonym retrieval task: the vector cosine, a baseline implementing the co-occurrence hypothesis, and a random rank. This paper describes the algorithm in details and analyzes its current limitations, suggesting that extensions may be developed for discriminating antonyms not only from near-synonyms but also from other semantic relations. During the evaluation, we have noticed that APAnt also has a particular preference for hypernyms.
format	article
author	Enrico Santus Qin Lu Alessandro Lenci Chu-Ren Huang
author_facet	Enrico Santus Qin Lu Alessandro Lenci Chu-Ren Huang
author_sort	Enrico Santus
title	When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
title_short	When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
title_full	When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
title_fullStr	When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
title_full_unstemmed	When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs
title_sort	when similarity becomes opposition: synonyms and antonyms discrimination in dsms
publisher	Accademia University Press
publishDate	2015
url	https://doaj.org/article/3db40347814b4e6fa403e75647f18eed
work_keys_str_mv	AT enricosantus whensimilaritybecomesoppositionsynonymsandantonymsdiscriminationindsms AT qinlu whensimilaritybecomesoppositionsynonymsandantonymsdiscriminationindsms AT alessandrolenci whensimilaritybecomesoppositionsynonymsandantonymsdiscriminationindsms AT churenhuang whensimilaritybecomesoppositionsynonymsandantonymsdiscriminationindsms
_version_	1718397939840188416

When Similarity Becomes Opposition: Synonyms and Antonyms Discrimination in DSMs

Ejemplares similares