Merging Verb Senses of Hindi WordNet using Word Embeddings.

Sudha Bhingardive; Ratish Puduppully; Dhirendra Singh; Pushpak Bhattacharyya

Merging Verb Senses of Hindi WordNet using Word Embeddings.

Sudha Bhingardive
, Ratish Puduppully
, Dhirendra Singh
, Pushpak Bhattacharyya

Indian Institute of Technology Bombay

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

In this paper, we present an approach for merging fine-grained verb senses of Hindi WordNet. Senses are merged based on gloss similarity score. We explore the use of word embeddings for gloss similarity computation and compare with various WordNet based gloss similarity measures.

Our results indicate that word embeddings show significant improvement over WordNet based measures. Consequently, we observe an increase in accuracy on merging fine-grained senses. Gold standard data constructed for our experiments is made available.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the 11th International Conference on Natural Language Processing
Publication date	2014
Pages	344-352
Publication status	Published - 2014
Externally published	Yes

Keywords

Hindi WordNet
word sense merging
gloss similarity
word embeddings
semantic similarity

Access to Document

Cite this

@inproceedings{a51fbe9de41b45ab91cac17e54208026,

title = "Merging Verb Senses of Hindi WordNet using Word Embeddings.",

abstract = "In this paper, we present an approach for merging fine-grained verb senses of Hindi WordNet. Senses are merged based on gloss similarity score. We explore the use of word embeddings for gloss similarity computation and compare with various WordNet based gloss similarity measures. Our results indicate that word embeddings show significant improvement over WordNet based measures. Consequently, we observe an increase in accuracy on merging fine-grained senses. Gold standard data constructed for our experiments is made available.",

keywords = "Hindi WordNet, word sense merging, gloss similarity, word embeddings, semantic similarity",

author = "Sudha Bhingardive and Ratish Puduppully and Dhirendra Singh and Pushpak Bhattacharyya",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2014",

language = "Udefineret/Ukendt",

pages = "344--352",

booktitle = "Proceedings of the 11th International Conference on Natural Language Processing",

}

TY - GEN

T1 - Merging Verb Senses of Hindi WordNet using Word Embeddings.

AU - Bhingardive, Sudha

AU - Puduppully, Ratish

AU - Singh, Dhirendra

AU - Bhattacharyya, Pushpak

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2014

Y1 - 2014

N2 - In this paper, we present an approach for merging fine-grained verb senses of Hindi WordNet. Senses are merged based on gloss similarity score. We explore the use of word embeddings for gloss similarity computation and compare with various WordNet based gloss similarity measures. Our results indicate that word embeddings show significant improvement over WordNet based measures. Consequently, we observe an increase in accuracy on merging fine-grained senses. Gold standard data constructed for our experiments is made available.

AB - In this paper, we present an approach for merging fine-grained verb senses of Hindi WordNet. Senses are merged based on gloss similarity score. We explore the use of word embeddings for gloss similarity computation and compare with various WordNet based gloss similarity measures. Our results indicate that word embeddings show significant improvement over WordNet based measures. Consequently, we observe an increase in accuracy on merging fine-grained senses. Gold standard data constructed for our experiments is made available.

KW - Hindi WordNet

KW - word sense merging

KW - gloss similarity

KW - word embeddings

KW - semantic similarity

M3 - Konferencebidrag i proceedings

SP - 344

EP - 352

BT - Proceedings of the 11th International Conference on Natural Language Processing

ER -