# Improving Natural Language Inference with a Pretrained Parser

arXiv: https://arxiv.org/abs/1909.08217 · HTML: https://mlsanity.com/paper/1909.08217/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

## Built on by (most cited first, 5 of 5)

- [The Limitations of Limited Context for Constituency Parsing](https://mlsanity.com/paper/2106.01580/) (2021)
- [Transfer learning for conflict and duplicate detection in software requirement pairs](https://mlsanity.com/paper/2301.03709/) (2023)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference](https://mlsanity.com/paper/2108.01589/) (2021)
- [Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork](https://mlsanity.com/paper/2610.16547/) (2026)

## Abstract (arXiv)

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.