papers AI Learner
The Github is limit! Click to go to the new site.

Target-Guided Open-Domain Conversation

2019-05-28
Jianheng Tang, Tiancheng Zhao, Chengyan Xiong, Xiaodan Liang, Eric P. Xing, Zhiting Hu

Abstract

Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat agents. In particular, we want a conversational system to chat naturally with human and proactively guide the conversation to a designated target subject. The problem is challenging as no public data is available for learning such a target-guided strategy. We propose a structured approach that introduces coarse-grained keywords to control the intended content of system responses. We then attain smooth conversation transition through turn-level supervised learning, and drive the conversation towards the target with discourse-level constraints. We further derive a keyword-augmented conversation dataset for the study. Quantitative and human evaluations show our system can produce meaningful and effective conversations, significantly improving over other approaches.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.11553

PDF

https://arxiv.org/pdf/1905.11553


Comments

Content