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 2108.04812cs.CLcs.AIcs.LG
收藏

通过观察人类跟随行为来持续学习以生成基础指令

Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Cornell University(康奈尔大学);Cornell Tech(康奈尔科技学院)

Noriyuki Kojima, Alane Suhr, Yoav Artzi

摘要:

通过观察人类用户的指令执行,我们研究了自然语言指令生成的持续学习。我们专注于一个协作的情况下,系统的行为和委托任务给人类用户使用自然语言。我们将用户执行生成的指令与原始系统意图进行比较,作为系统成功传达其意图的指示。我们展示了如何使用这个信号来提高系统的能力,通过上下文强盗学习生成指令。在与真实用户的交互中,我们的系统随着时间的推移在生成语言的能力上表现出了显着的改进。

英文摘要:

We study continual learning for natural language instruction generation, by observing human users' instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system's success communicating its intent. We show how to use this signal to improve the system's ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.

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。

↑