Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
This work addresses the problem of sentence representation for natural language understanding, showing strong performance in a shared task and on a benchmark dataset, but it is incremental as it builds on existing neural network methods.
The paper tackled natural language inference by developing a recurrent neural network-based sentence encoder with gated attention, achieving top results in the RepEval 2017 Shared Task with 74.9% accuracy on both in-domain and cross-domain test sets and 85.5% accuracy on the SNLI dataset under specific conditions.
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task. This paper describes our system (alpha) that is ranked among the top in the Shared Task, on both the in-domain test set (obtaining a 74.9% accuracy) and on the cross-domain test set (also attaining a 74.9% accuracy), demonstrating that the model generalizes well to the cross-domain data. Our model is equipped with intra-sentence gated-attention composition which helps achieve a better performance. In addition to submitting our model to the Shared Task, we have also tested it on the Stanford Natural Language Inference (SNLI) dataset. We obtain an accuracy of 85.5%, which is the best reported result on SNLI when cross-sentence attention is not allowed, the same condition enforced in RepEval 2017.