Target-Guided Open-Domain Conversation
This addresses the need for goal-oriented conversation systems in applications like psychotherapy and education, representing an incremental advance in controlling dialogue flow.
The paper tackles the problem of enabling open-domain chat agents to proactively guide conversations towards a designated target subject, such as for recommendation or education, by proposing a structured approach using coarse-grained keywords and discourse-level constraints, resulting in significant improvements over other methods in producing meaningful and effective conversations as shown in evaluations.
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.