Learning to Align Question and Answer Utterances in Customer Service Conversation with Recurrent Pointer Networks | |
Shizhu HE1; Kang Liu1,2; Weiting An3 | |
2019-01-27 | |
会议日期 | 2019.01.27 - 2019.02.01 |
会议地点 | Honolulu, Hawaii, USA |
英文摘要 | Customers ask questions, and customer service staffs answer those questions. It is the basic service manner of customer service (CS). The progress of CS is a typical multi-round con- versation. However, there are no explicit corresponding rela- tions among conversational utterances. This paper focuses on obtaining explicit alignments of question and answer utter- ances in CS. It not only is an important task of dialogue analy- sis, but also able to obtain lots of valuable train data for learn- ing dialogue systems. In this work, we propose end-to-end models for aligning question (Q) and answer (A) utterances in CS conversation with recurrent pointer networks (RPN). On the one hand, RPN-based alignment models are able to model the conversational contexts and the mutual influence of different Q-A alignments. On the other hand, they are able to address the issue of empty and multiple alignments for some utterances in a unified manner. We construct a dataset from an in-house online CS. The experimental results demonstrate that the proposed models are effective to learn the alignments of question and answer utterances. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57451] |
专题 | 复杂系统认知与决策实验室 |
作者单位 | 1.Institute of Automation, Chinese Academy of Science 2.University of Chinese Academy of Sciences 3.Alibaba Group |
推荐引用方式 GB/T 7714 | Shizhu HE,Kang Liu,Weiting An. Learning to Align Question and Answer Utterances in Customer Service Conversation with Recurrent Pointer Networks[C]. 见:. Honolulu, Hawaii, USA. 2019.01.27 - 2019.02.01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论