Attention Boosted Sequential Inference Model
This work addresses natural language inference for NLP researchers, but it is incremental as it builds upon the existing ESIM model with added attention mechanisms.
The paper tackled the problem of natural language inference by enhancing the ESIM model with word attention and adaptive direction-oriented attention mechanisms, resulting in superior performance over the original ESIM on SNLI, MultiNLI, and Quora benchmarks.
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.