Improving Natural Language Inference with a Pretrained Parser
This work addresses the challenge of enhancing NLI performance for AI researchers, but it is incremental as it builds on existing models with a new integration method.
The paper tackled the problem of improving natural language inference models by incorporating syntax from a pretrained dependency parser, resulting in consistent accuracy gains across multiple models and benchmarks.
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.