Distance-based Self-Attention Network for Natural Language Inference

TL;DR

This paper introduces a distance-based self-attention network for natural language inference that incorporates word distance information, achieving state-of-the-art results on SNLI and excelling with long sentences.

Contribution

It proposes a novel distance mask in self-attention to better model local dependencies without sacrificing global context understanding.

Findings

Achieved new state-of-the-art on SNLI dataset.

Enhanced performance on long sentences and documents.

Demonstrated effectiveness of distance masking in self-attention.

Abstract

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time by solely using attention. Motivated by the Transformer, Directional Self Attention Network (Shen et al., 2017), a fully attention-based sentence encoder, was proposed. It showed good performance with various data by using forward and backward directional information in a sentence. But in their study, not considered at all was the distance between words, an important feature when learning the local dependency to help understand the context of input text. We propose Distance-based Self-Attention Network, which considers the word distance by using a simple distance mask in order to model the local dependency without losing the ability of modeling global dependency which attention has inherent. Our model shows good performance with NLI data, and it records the new state-of-the-art result with SNLI data. Additionally, we show that our model has a strength in long sentences or documents.