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

Sudha Rao, Hal Daumé III


Abstract
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.
Anthology ID:
P18-1255
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2737–2746
URL:
https://www.aclweb.org/anthology/P18-1255
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
Note:
 P18-1255.Notes.pdf
Video:
 https://vimeo.com/288152796
Presentation:
 P18-1255.Presentation.pdf