Inner Attention based Recurrent Neural Networks for Answer Selection

@inproceedings{Wang2016InnerAB,
  title={Inner Attention based Recurrent Neural Networks for Answer Selection},
  author={Bingning Wang and Kang Liu and Jun Zhao},
  booktitle={ACL},
  year={2016}
}
  • Bingning Wang, Kang Liu, Jun Zhao
  • Published in ACL 2016
  • Computer Science
  • Attention based recurrent neural networks have shown advantages in representing natural language sentences (Hermann et al., 2015; Rocktäschel et al., 2015; Tan et al., 2015). Based on recurrent neural networks (RNN), external attention information was added to hidden representations to get an attentive sentence representation. Despite the improvement over nonattentive models, the attention mechanism under RNN is not well studied. In this work, we analyze the deficiency of traditional attention… CONTINUE READING
    159 Citations
    Enhancing Recurrent Neural Networks with Positional Attention for Question Answering
    • 51
    • Highly Influenced
    Knowledge Memory Based LSTM Model for Answer Selection
    • 2
    Double attention recurrent convolution neural network for answer selection
    • 1
    Context-Aware Answer Sentence Selection With Hierarchical Gated Recurrent Neural Networks
    • 17
    CA-RNN: Using Context-Aligned Recurrent Neural Networks for Modeling Sentence Similarity
    • 19
    • Highly Influenced
    • PDF
    Gated Group Self-Attention for Answer Selection
    • 2
    • PDF
    Transformer-Based Neural Network for Answer Selection in Question Answering
    • 15
    • Highly Influenced
    • PDF
    Entire Information Attentive GRU for Text Representation
    • 6

    References

    SHOWING 1-10 OF 31 REFERENCES
    Attentive Pooling Networks
    • 240
    • PDF
    Occam's Gates
    • 1
    • PDF
    Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
    • 860
    • PDF
    An Empirical Exploration of Recurrent Network Architectures
    • 1,168
    • PDF
    End-To-End Memory Networks
    • 1,657
    • PDF
    LSTM-based Deep Learning Models for non-factoid answer selection
    • 336
    • Highly Influential
    • PDF
    ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
    • 585
    • Highly Influential
    • PDF
    Extensions of recurrent neural network language model
    • 1,236
    • PDF
    Memory Networks
    • 982
    • PDF
    Contextual LSTM (CLSTM) models for Large scale NLP tasks
    • 148
    • Highly Influential
    • PDF