Target-Guided Open-Domain Conversation Planning
Target-Guided Open-Domain Conversation Planning
复制标题
DOI：
10.48550/arxiv.2209.09746
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Yosuke Kishinami;Reina Akama;Shiki Sato;Ryoko Tokuhisa;Jun Suzuki;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Yosuke Kishinami;Reina Akama;Shiki Sato;Ryoko Tokuhisa;Jun Suzuki;Kentaro Inui
以前的研究解决面向目标的会话任务缺乏一个重要的概念，已深入研究的背景下，面向目标的人工智能代理，即规划。在这项研究中，我们提出了目标引导的开放域会话规划（TGCP）任务，以评估神经会话代理是否具有目标导向的会话规划能力。使用TGCP任务，我们调查现有的检索模型和最近的强生成模型的会话规划能力。实验结果揭示了当前技术面临的挑战。
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.