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 1810.02017cs.ROcs.HC
收藏

人机对话采集效率与覆盖率的平衡

Balancing Efficiency and Coverage in Human-Robot Dialogue Collection

U.S. Army Research Laboratory(美国陆军研究实验室);USC Institute for Creative Technologies(南加州大学创意技术研究所);Tufts University(塔夫茨大学)
Matthew Marge, Claire Bonial, Stephanie Lukin, Cory Hayes, Ashley Foots, Ron Artstein, Cassidy Henry, Kimberly Pollard, Carla Gordon, Felix Gervits, Anton Leusk… 展开作者

Matthew Marge, Claire Bonial, Stephanie Lukin, Cory Hayes, Ashley Foots, Ron Artstein, Cassidy Henry, Kimberly Pollard, Carla Gordon, Felix Gervits, Anton Leuski, Susan Hill, Clare Voss, David Traum

摘要:

我们描述了一个多阶段的绿野仙踪的方法来收集人与机器人的对话,在协作搜索和导航任务。这些数据正被用于训练一个初始的自动化机器人对话系统,以支持协作探索任务。在第一阶段,一个向导自由地键入机器人的话语给人类参与者。在第二阶段,这些数据用于设计GUI,其中包括用于最常见通信的按钮,以及用于具有不同参数的通信的模板。在这些阶段收集的数据的比较表明,GUI实现了更快的对话速度,同时仍然保持适当的响应的高覆盖率,使更有效的有针对性的数据汇集,并使用GUI收集的数据在自然语言理解方面的改进。作为一个有前途的第一步,互动学习,这项工作表明,我们的方法,使有用的训练数据收集基于导航的HRI任务。

英文摘要:

We describe a multi-phased Wizard-of-Oz approach to collecting human-robot dialogue in a collaborative search and navigation task. The data is being used to train an initial automated robot dialogue system to support collaborative exploration tasks. In the first phase, a wizard freely typed robot utterances to human participants. For the second phase, this data was used to design a GUI that includes buttons for the most common communications, and templates for communications with varying parameters. Comparison of the data gathered in these phases show that the GUI enabled a faster pace of dialogue while still maintaining high coverage of suitable responses, enabling more efficient targeted data collection, and improvements in natural language understanding using GUI-collected data. As a promising first step towards interactive learning, this work shows that our approach enables the collection of useful training data for navigation-based HRI tasks.

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。

↑