Improving distributed representation of word sense via WordNet Gloss composition and context clustering

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations Save citation

Authors

Research units

Abstract

In recent years, there has been an increas-ing interest in learning a distributed rep-resentation of word sense. Traditional context clustering based models usually require careful tuning of model parame-ters, and typically perform worse on infre-quent word senses. This paper presents a novel approach which addresses these lim-itations by first initializing the word sense embeddings through learning sentence-level embeddings from WordNet glosses using a convolutional neural networks. The initialized word sense embeddings are used by a context clustering based model to generate the distributed representations of word senses. Our learned represen-tations outperform the publicly available embeddings on 2 out of 4 metrics in the word similarity task, and 6 out of 13 sub tasks in the analogical reasoning task.

Request a copy

Request a copy

Details

Publication date2015
Publication titleProceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Short Papers)
PublisherAssociation for Computational Linguistics
Pages15-20
Number of pages6
Volume2
ISBN (Print)978-1-941643-73-0
Original languageEnglish
Event53rd annual meeting of the Association for Computational Linguistics / 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing - Beijing, China

Meeting

Meeting53rd annual meeting of the Association for Computational Linguistics / 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing
Abbreviated titleACL-IJCNLP 2015
CountryChina
CityBeijing
Period26/07/1531/07/15

Employable Graduates; Exploitable Research

Copy the text from this field...