Enhancing generative conversational service agents with dialog history and external knowledge

Zongsheng Wang, Zhuoran Wang, Yinong Long, Jianan Wang, Zhen Xu, Baoxun Wang

Abstract: Highlights • In this paper, we design two dialog systems that capture either history information directly from the dialog. or external knowledge extracted from a search engine. • Two improved sequence-to-sequence frameworks are constructed to generate more informative responses based on the captured history information or external knowledge, based on the dataset provided in DSTC6-Track2. • To further prove the efficacy of proposed model on long-turn dialogs, the Ubuntu dataset is used to implement additional experiments. • Based on the experiment results, we make detailed case studies and error analysis and propose promising solutions. Abstract For generative conversational agents, especially service-oriented systems, it is of great importance to improve the informativeness of generated responses and avoid bland results. In this paper, we describe our attempt at generating natural and informative responses for customer service oriented dialog systems, by incorporating dialog history related information and external knowledge. Two improved sequence-to-sequence frameworks are proposed to generate responses based on extra information in addition to the current user input, one encodes the entire dialogue history, while the other integrates external knowledge extracted from a search engine. The experimental results on the DSCT6-Track2 and Ubuntu Dialog corpora demonstrate that the proposed systems are promising to generate more informative responses. However, case studies suggest that some particular features of the proposed systems and the datasets might restrict the systems to fully exploit such extra information.