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 1805.04655cs.CL
收藏

学习提出好问题:使用完美信息的神经期望值对澄清问题进行排名

Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information

University of Maryland, College Park(马里兰大学帕克分校);Microsoft Research(微软研究院)

Sudha Rao, Hal Daumé

摘要:

询问是沟通的基础,除非机器能提出问题,否则它们无法与人类有效合作。在这项工作中,我们建立了一个神经网络模型的任务排名澄清问题。我们的模型受到完美信息期望值的启发:一个好问题是一个期望答案将是有用的。我们使用StackExchange的数据来研究这个问题,StackExchange是一个丰富的在线资源,人们经常向帖子提出澄清问题,以便他们可以更好地为原始发帖者提供帮助。我们创建了一个澄清问题的数据集,由来自StackExchange三个域的~ 77 K帖子和澄清问题(和答案)组成:askubuntu,unix和超级用户。我们对该数据集的500个样本进行了评估,并对专家的判断进行了评估,结果表明,与受控基线相比,我们的模型有了显着的改进。

英文摘要:

Inquiry is fundamental to communication, and machines cannot effectively collaborate with humans unless they can ask questions. In this work, we build a neural network model for the task of ranking clarification questions. Our model is inspired by the idea of expected value of perfect information: a good question is one whose expected answer will be useful. We study this problem using data from StackExchange, a plentiful online resource in which people routinely ask clarifying questions to posts so that they can better offer assistance to the original poster. We create a dataset of clarification questions consisting of ~77K posts paired with a clarification question (and answer) from three domains of StackExchange: askubuntu, unix and superuser. We evaluate our model on 500 samples of this dataset against expert human judgments and demonstrate significant improvements over controlled baselines.

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。

↑