Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

@inproceedings{Tay2018HyperbolicRL,
  title={Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering},
  author={Yi Tay and Luu Anh Tuan and Siu Cheung Hui},
  booktitle={WSDM},
  year={2018}
}
The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new word interaction layers or attention-based matching mechanisms, it seems to be a well-established fact that these components are mandatory for good performance. Unfortunately, the memory and computation cost incurred by these complex mechanisms are undesirable for practical… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 34 times over the past 90 days. VIEW TWEETS

Similar Papers

Loading similar papers…