Distance-based Self-Attention Network for Natural Language Inference
This work addresses the challenge of capturing local context in attention-based models for natural language inference, which is an incremental improvement over existing attention mechanisms.
The authors tackled the problem of modeling local dependencies in natural language inference by proposing a distance-based self-attention network that incorporates word distance using a distance mask, achieving state-of-the-art results on SNLI data and showing strength in handling long sentences or documents.
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.