Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
This work addresses text entailment recognition for NLP applications, representing an incremental improvement over prior methods.
The paper tackled natural language inference by proposing a sentence encoding model with a two-stage process using bidirectional LSTM and inner-attention, which outperformed the existing best sentence encoding-based approach on the SNLI Corpus with fewer parameters.
In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooling was used over word-level bidirectional LSTM (biLSTM) to generate a first-stage sentence representation. Secondly, attention mechanism was employed to replace average pooling on the same sentence for better representations. Instead of using target sentence to attend words in source sentence, we utilized the sentence's first-stage representation to attend words appeared in itself, which is called "Inner-Attention" in our paper . Experiments conducted on Stanford Natural Language Inference (SNLI) Corpus has proved the effectiveness of "Inner-Attention" mechanism. With less number of parameters, our model outperformed the existing best sentence encoding-based approach by a large margin.