Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference

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.

PDF Abstract WS 2017 PDF WS 2017 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference SNLI 600D (300+300) Deep Gated Attn. BiLSTM encoders % Test Accuracy 85.5 # 71
% Train Accuracy 90.5 # 44
Parameters 12m # 4


No methods listed for this paper. Add relevant methods here