Natural Language Inference with Definition Embedding Considering Context On the Fly

Kosuke Nishida, Kyosuke Nishida, Hisako Asano, Junji Tomita


Abstract
Natural language inference (NLI) is one of the most important tasks in NLP. In this study, we propose a novel method using word dictionaries, which are pairs of a word and its definition, as external knowledge. Our neural definition embedding mechanism encodes input sentences with the definitions of each word of the sentences on the fly. It can encode the definition of words considering the context of input sentences by using an attention mechanism. We evaluated our method using WordNet as a dictionary and confirmed that our method performed better than baseline models when using the full or a subset of 100d GloVe as word embeddings.
Anthology ID:
W18-3007
Volume:
Proceedings of the Third Workshop on Representation Learning for NLP
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Kiros, Hongyuan Mei, Dipendra Misra
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–63
Language:
URL:
https://aclanthology.org/W18-3007
DOI:
10.18653/v1/W18-3007
Bibkey:
Cite (ACL):
Kosuke Nishida, Kyosuke Nishida, Hisako Asano, and Junji Tomita. 2018. Natural Language Inference with Definition Embedding Considering Context On the Fly. In Proceedings of the Third Workshop on Representation Learning for NLP, pages 58–63, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Natural Language Inference with Definition Embedding Considering Context On the Fly (Nishida et al., RepL4NLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/W18-3007.pdf
Data
MultiNLISNLI