Open-domain clarification question generation without question examples

Julia White, Gabriel Poesia, Robert Hawkins, Dorsa Sadigh, Noah Goodman


Abstract
An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of uncertainty, humans engage in an interactive process known as repair: asking questions and seeking clarification until their uncertainty is resolved. We propose a framework for building a visually grounded question-asking model capable of producing polar (yes-no) clarification questions to resolve misunderstandings in dialogue. Our model uses an expected information gain objective to derive informative questions from an off-the-shelf image captioner without requiring any supervised question-answer data. We demonstrate our model’s ability to pose questions that improve communicative success in a goal-oriented 20 questions game with synthetic and human answerers.
Anthology ID:
2021.emnlp-main.44
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
563–570
Language:
URL:
https://aclanthology.org/2021.emnlp-main.44
DOI:
10.18653/v1/2021.emnlp-main.44
Bibkey:
Cite (ACL):
Julia White, Gabriel Poesia, Robert Hawkins, Dorsa Sadigh, and Noah Goodman. 2021. Open-domain clarification question generation without question examples. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 563–570, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Open-domain clarification question generation without question examples (White et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.44.pdf
Data
COCOShapeWorld