We introduce a novel approach to incorporate syntax into natural language inference (NLI) models. Our method uses contextual token-level vector representations from a pretrained dependency parser. Like other contextual embedders, our method is broadly applicable to any neural model. We experiment with four strong NLI models (decomposable attention model, ESIM, BERT, and MT-DNN), and show consistent benefit to accuracy across three NLI benchmarks.
@article{arxiv.1909.08217,
title = {Improving Natural Language Inference with a Pretrained Parser},
author = {Deric Pang and Lucy H. Lin and Noah A. Smith},
journal= {arXiv preprint arXiv:1909.08217},
year = {2019}
}