Corpus ID: 209376176

Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering

@article{Wang2020ImprovingKD,
  title={Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering},
  author={Jia-xiang Wang and Junhao Liu and Wei Bi and Xiaojiang Liu and Kejing He and Ruifeng Xu and Min Yang},
  journal={ArXiv},
  year={2020},
  volume={abs/1912.07491}
}
  • Jia-xiang Wang, Junhao Liu, +4 authors Min Yang
  • Published in AAAI 2020
  • Computer Science
  • Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv