English

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

Computation and Language 2018-05-08 v2

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.

Keywords

Cite

@article{arxiv.1804.09779,
  title  = {On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference},
  author = {Adam Poliak and Yonatan Belinkov and James Glass and Benjamin Van Durme},
  journal= {arXiv preprint arXiv:1804.09779},
  year   = {2018}
}

Comments

To be presented at NAACL 2018 - 11 pages