Enhanced LSTM for Natural Language Inference

TL;DR

This paper introduces an enhanced LSTM-based model for natural language inference that achieves state-of-the-art accuracy by combining sequential and recursive architectures, with syntactic parsing information further boosting performance.

Contribution

It demonstrates that carefully designed chain LSTM models can outperform complex architectures, and that recursive structures with syntactic parsing improve inference accuracy.

Findings

Achieved 88.6% accuracy on SNLI dataset.

Sequential LSTM models outperform previous complex models.

Recursive architectures with parsing information further improve results.

Abstract

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result---it further improves the performance even when added to the already very strong model.