0

Target-Guided Open-Domain Conversation Planning

The study evaluates the goal-oriented conversation planning abilities of neural conversational agents using a novel Target-Guided Open-Domain Conversation Planning (TGCP) task, highlighting the shortcomings of current models.

Year
2022
Venue
COLING 2022 10
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2209.09746ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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.

Authors

6