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
- Language:
- URL:
- https://aclanthology.org/P18-1255
- DOI:
- 10.18653/v1/P18-1255
- Cite (ACL):
- Sudha Rao and Hal Daumé III. 2018. Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2737–2746, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information (Rao & Daumé III, ACL 2018)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/P18-1255.pdf
- Code
- raosudha89/ranking_clarification_questions