CLSep 20, 2022

Target-Guided Open-Domain Conversation Planning

arXiv:2209.09746v1584 citationsh-index: 43
Originality Synthesis-oriented
AI Analysis

This addresses the problem of evaluating goal-oriented conversation planning in AI agents, which is incremental as it builds on prior target-oriented conversational tasks by incorporating planning concepts.

The paper introduced the Target-Guided Open-Domain Conversation Planning (TGCP) task to assess goal-oriented planning in neural conversational agents, and found that existing retrieval and generative models face significant challenges in this area.

Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning. In this study, we propose the task of Target-Guided Open-Domain Conversation Planning (TGCP) task to evaluate whether neural conversational agents have goal-oriented conversation planning abilities. Using the TGCP task, we investigate the conversation planning abilities of existing retrieval models and recent strong generative models. The experimental results reveal the challenges facing current technology.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes