Topic Models for Meaning Similarity in Context

Georgiana Dinu; Mirella Lapata

Topic Models for Meaning Similarity in Context

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Recent work on distributional methods for similarity focuses on using the context in which a target word occurs to derive context-sensitive similarity computations. In this paper we present a method for computing similarity which builds vector representations for words in context by modelling senses as latent variables in a large corpus. We apply this to the Lexical Substitution Task and we show that our model significantly outperforms typical distributional methods.

Original language	English
Title of host publication	COLING 2010, 23rd International Conference on Computational Linguistics, Posters Volume, 23-27 August 2010, Beijing, China
Publisher	Association for Computational Linguistics
Pages	250-258
Number of pages	9
Publication status	Published - 2010

Access to Document

2010_Dinu_Lapata_Topic Models for Meaning Similarity in ContextFinal published version, 299 KB

http://aclweb.org/anthology-new/C/C10/C10-2029.pdf

Cite this

@inproceedings{db6dd6b85492428aad421d130fdb5bbc,

title = "Topic Models for Meaning Similarity in Context",

abstract = "Recent work on distributional methods for similarity focuses on using the context in which a target word occurs to derive context-sensitive similarity computations. In this paper we present a method for computing similarity which builds vector representations for words in context by modelling senses as latent variables in a large corpus. We apply this to the Lexical Substitution Task and we show that our model significantly outperforms typical distributional methods. ",

author = "Georgiana Dinu and Mirella Lapata",

year = "2010",

language = "English",

pages = "250--258",

booktitle = "COLING 2010, 23rd International Conference on Computational Linguistics, Posters Volume, 23-27 August 2010, Beijing, China",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Topic Models for Meaning Similarity in Context

AU - Dinu, Georgiana

AU - Lapata, Mirella

PY - 2010

Y1 - 2010

N2 - Recent work on distributional methods for similarity focuses on using the context in which a target word occurs to derive context-sensitive similarity computations. In this paper we present a method for computing similarity which builds vector representations for words in context by modelling senses as latent variables in a large corpus. We apply this to the Lexical Substitution Task and we show that our model significantly outperforms typical distributional methods.

AB - Recent work on distributional methods for similarity focuses on using the context in which a target word occurs to derive context-sensitive similarity computations. In this paper we present a method for computing similarity which builds vector representations for words in context by modelling senses as latent variables in a large corpus. We apply this to the Lexical Substitution Task and we show that our model significantly outperforms typical distributional methods.

M3 - Conference contribution

SP - 250

EP - 258

BT - COLING 2010, 23rd International Conference on Computational Linguistics, Posters Volume, 23-27 August 2010, Beijing, China

PB - Association for Computational Linguistics

ER -

Topic Models for Meaning Similarity in Context

Abstract

Access to Document

Fingerprint

Cite this