Distance-based Self-Attention Network for Natural Language Inference

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.

12 pages, 13 figures

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Layer Normalization
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• Dynamic Routing Between Capsules
• Shortcut-Stacked Sentence Encoders for Multi-Domain Inference
• Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference

Cited by in corpus (4)

• Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
• Towards Open Intent Discovery for Conversational Text
• TextNAS: A Neural Architecture Search Space tailored for Text Representation
• SNU_IDS at SemEval-2019 Task 3: Addressing Training-Test Class Distribution Mismatch in Conversational Classification