[go: up one dir, main page]

Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar


Abstract
Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.
Anthology ID:
P19-1320
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3308–3318
Language:
URL:
https://aclanthology.org/P19-1320
DOI:
10.18653/v1/P19-1320
Bibkey:
Cite (ACL):
Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, and Partha Talukdar. 2019. Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3308–3318, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks (Vashishth et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1320.pdf
Supplementary:
 P19-1320.Supplementary.pdf
Code
 malllabiisc/WordGCN
Data
SQuAD