Corpus ID: 17336459

Topic Augmented Neural Network for Short Text Conversation

@article{Wu2016TopicAN,
  title={Topic Augmented Neural Network for Short Text Conversation},
  author={Yuehua Wu and W. Wu and Zhoujun Li and M. Zhou},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.00090}
}
  • Yuehua Wu, W. Wu, +1 author M. Zhou
  • Published 2016
  • Computer Science
  • ArXiv
  • Message response matching is an important task within retrieval-based chatbots. [...] Key Method In TANN, the sentence embedding layer embeds an input message and a response into a vector space, while the topic embedding layer forms a topic vector by a linear combination of the embedding of topic words whose weights are determined by both themselves and the message vector. The message vector, the response vector, and the topic vector are then fed to the matching layer to calculate a matching score. The…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 13 CITATIONS

    Enhanced Matching Network for Multi-turn Response Selection in Retrieval-Based Chatbots

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Single turn Chinese emotional conversation generation based on information retrieval and question answering

    VIEW 1 EXCERPT
    CITES BACKGROUND