Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

@article{Liu2016LearningNL,
  title={Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention},
  author={Yang Liu and Chengjie Sun and Lei Lin and Xiaolong Wang},
  journal={CoRR},
  year={2016},
  volume={abs/1605.09090}
}

• Yang Liu, Chengjie Sun, +1 author Xiaolong Wang
• Published 2016 in ArXiv

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 firststage 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… CONTINUE READING

Save to Library

Create Alert

Cite

View on ArXiv