arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.08373cs.CLcs.LG
收藏

从自然语言监督学习语义分析器

Learning to Learn Semantic Parsers from Natural Language Supervision

LAER AI, Inc.(LAER人工智能公司);Carnegie Mellon University(卡内基梅隆大学)

Igor Labutov, Bishan Yang, Tom Mitchell

摘要:

作为人类,我们经常依靠语言来学习语言。例如,当在对话中被纠正时,我们可以从纠正中学习,随着时间的推移提高我们的语言流利性。受此启发,我们提出了一个学习算法,用于训练语义分析器从监督(反馈)表示在自然语言。我们的算法从用户的更正中学习语义解析器,例如“不,我真正的意思是在他工作之前,而不是之后”,同时学习解析这种自然语言反馈,以利用它作为一种监督形式。与金标准的逻辑形式的监督,我们的方法不需要用户熟悉的基本逻辑形式主义,从外延监督不同,它不需要用户知道正确的答案,他们的查询。这使得我们的学习算法在现有会话日志可用并且可以用作训练数据的设置中自然地可扩展。我们构建了一个新的数据集的自然语言反馈的对话设置,并表明我们的方法是有效的学习语义解析器从这样的自然语言监督。

英文摘要:

As humans, we often rely on language to learn language. For example, when corrected in a conversation, we may learn from that correction, over time improving our language fluency. Inspired by this observation, we propose a learning algorithm for training semantic parsers from supervision (feedback) expressed in natural language. Our algorithm learns a semantic parser from users' corrections such as "no, what I really meant was before his job, not after", by also simultaneously learning to parse this natural language feedback in order to leverage it as a form of supervision. Unlike supervision with gold-standard logical forms, our method does not require the user to be familiar with the underlying logical formalism, and unlike supervision from denotation, it does not require the user to know the correct answer to their query. This makes our learning algorithm naturally scalable in settings where existing conversational logs are available and can be leveraged as training data. We construct a novel dataset of natural language feedback in a conversational setting, and show that our method is effective at learning a semantic parser from such natural language supervision.

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。

↑