Response Generation by Context-Aware Prototype Editing


  • Yu Wu Beihang University
  • Furu Wei Microsoft Research Asia
  • Shaohan Huang Microsoft Research Asia
  • Yunli Wang Beihang University
  • Zhoujun Li Beihang University
  • Ming Zhou Microsoft Research



Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm, prototypethen-edit for response generation, that first retrieves a prototype response from a pre-defined index and then edits the prototype response according to the differences between the prototype context and current context. Our motivation is that the retrieved prototype provides a good start-point for generation because it is grammatical and informative, and the post-editing process further improves the relevance and coherence of the prototype. In practice, we design a contextaware editing model that is built upon an encoder-decoder framework augmented with an editing vector. We first generate an edit vector by considering lexical differences between a prototype context and current context. After that, the edit vector and the prototype response representation are fed to a decoder to generate a new response. Experiment results on a large scale dataset demonstrate that our new paradigm significantly increases the relevance, diversity and originality of generation results, compared to traditional generative models. Furthermore, our model outperforms retrieval-based methods in terms of relevance and originality.




How to Cite

Wu, Y., Wei, F., Huang, S., Wang, Y., Li, Z., & Zhou, M. (2019). Response Generation by Context-Aware Prototype Editing. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7281-7288.



AAAI Technical Track: Natural Language Processing