Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
Refereed conference paper presented and published in conference proceedings


全文

其它資訊
摘要For dialogue response generation,traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.
出版社接受日期02.06.2019
著者Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi
會議名稱The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019)
會議開始日02.06.2019
會議完結日07.06.2019
會議地點Minneapolis
會議國家/地區美國
會議論文集題名Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics
出版年份2019
月份6
頁次1219 - 1228
語言英式英語

上次更新時間 2019-02-12 於 10:03