Neural Natural Language Inference Models Enhanced with External Knowledge

TL;DR

This paper enhances neural natural language inference models by integrating external knowledge, leading to improved performance on SNLI and MultiNLI datasets, addressing the challenge of models not learning all necessary knowledge from data alone.

Contribution

The paper introduces a method to incorporate external knowledge into neural NLI models, significantly boosting their inference accuracy.

Findings

Achieved state-of-the-art results on SNLI and MultiNLI datasets.

External knowledge integration improves model understanding and inference.

Models outperform previous approaches without external knowledge.

Abstract

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.