Attention Boosted Sequential Inference Model

5 Dec 2018  ·  Guanyu Li, Pengfei Zhang, Caiyan Jia ·

Attention mechanism has been proven effective on natural language processing. This paper proposes an attention boosted natural language inference model named aESIM by adding word attention and adaptive direction-oriented attention mechanisms to the traditional Bi-LSTM layer of natural language inference models, e.g. ESIM. This makes the inference model aESIM has the ability to effectively learn the representation of words and model the local subsentential inference between pairs of premise and hypothesis. The empirical studies on the SNLI, MultiNLI and Quora benchmarks manifest that aESIM is superior to the original ESIM model.

PDF Abstract
No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference MultiNLI aESIM Matched 73.9 # 31
Mismatched 73.9 # 27
Natural Language Inference Quora Question Pairs aESIM Accuracy 88.01 # 1
Natural Language Inference SNLI aESIM % Test Accuracy 88.1 # 33