Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference

Abstract

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There have been two lines of approaches that can be used to further address the limitation: (1) unsupervised pretraining can leverage knowledge in much larger unstructured text data; (2) structured (often human-curated) knowledge has started to be considered in neural-network-based models for NLI. An immediate question is whether these two approaches complement each other, or how to develop models that can bring together their advantages. In this paper, we propose models that leverage structured knowledge in different components of pre-trained models. Our results show that the proposed models perform better than previous BERT-based state-of-the-art models. Although our models are proposed for NLI, they can be easily extended to other sentence or sentence-pair classification problems.

References in corpus (8)

• Enhanced LSTM for Natural Language Inference
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Neural Natural Language Inference Models Enhanced with External Knowledge
• Stress Test Evaluation for Natural Language Inference
• Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
• Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
• Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference