arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.09566cs.HCcs.AIcs.CL
收藏

基于自然语言的人引导协同问题求解框架

Human-guided Collaborative Problem Solving: A Natural Language based Framework

University of Texas at Dallas(德克萨斯大学达拉斯分校);Microsoft Research India(微软印度研究院);Washington State University(华盛顿州立大学);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Pennsylvania(宾夕法尼亚大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Srira… 展开作者

Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Sriraam Natarajan, Martha Palmer, Dan Roth

摘要:

我们考虑的问题,人机协作问题解决的规划任务加上自然语言通信。我们的框架由三个组成部分-一个自然语言引擎,解析的语言话语的正式表示,反之亦然,一个概念学习者,诱导广义概念的计划的基础上有限的互动与用户,和一个HTN计划,解决了任务的基础上,人类的互动。我们说明了这个框架的能力,以解决协作解决问题的关键挑战,通过演示它在一个基于Minecraft的blocksworld域的协作建设任务。随附的演示视频可在https://youtu.be/q1pWe4aahF0上获得。

英文摘要:

We consider the problem of human-machine collaborative problem solving as a planning task coupled with natural language communication. Our framework consists of three components -- a natural language engine that parses the language utterances to a formal representation and vice-versa, a concept learner that induces generalized concepts for plans based on limited interactions with the user, and an HTN planner that solves the task based on human interaction. We illustrate the ability of this framework to address the key challenges of collaborative problem solving by demonstrating it on a collaborative building task in a Minecraft-based blocksworld domain. The accompanied demo video is available at https://youtu.be/q1pWe4aahF0.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑