On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference

Adam Poliak, Yonatan Belinkov, James Glass, Benjamin Van Durme


Abstract
We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena. We use these representations as features to train a natural language inference (NLI) classifier based on datasets recast from existing semantic annotations. In applying this process to a representative NMT system, we find its encoder appears most suited to supporting inferences at the syntax-semantics interface, as compared to anaphora resolution requiring world knowledge. We conclude with a discussion on the merits and potential deficiencies of the existing process, and how it may be improved and extended as a broader framework for evaluating semantic coverage
Anthology ID:
N18-2082
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
513–523
Language:
URL:
https://aclanthology.org/N18-2082
DOI:
10.18653/v1/N18-2082
Bibkey:
Cite (ACL):
Adam Poliak, Yonatan Belinkov, James Glass, and Benjamin Van Durme. 2018. On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 513–523, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (Poliak et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2082.pdf
Code
 boknilev/nmt-repr-analysis
Data
MultiNLISNLI