Answer-based Adversarial Training for Generating Clarification Questions

Sudha Rao, Hal Daumé III


Abstract
We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as latent variables can guide our approach into generating more useful clarification questions. We develop a Generative Adversarial Network (GAN) where the generator is a sequence-to-sequence model and the discriminator is a utility function that models the value of updating the context with the answer to the clarification question. We evaluate on two datasets, using both automatic metrics and human judgments of usefulness, specificity and relevance, showing that our approach outperforms both a retrieval-based model and ablations that exclude the utility model and the adversarial training.
Anthology ID:
N19-1013
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
143–155
Language:
URL:
https://aclanthology.org/N19-1013
DOI:
10.18653/v1/N19-1013
Bibkey:
Cite (ACL):
Sudha Rao and Hal Daumé III. 2019. Answer-based Adversarial Training for Generating Clarification Questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 143–155, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Answer-based Adversarial Training for Generating Clarification Questions (Rao & Daumé III, NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/N19-1013.pdf
Supplementary:
 N19-1013.Supplementary.pdf
Video:
 https://vimeo.com/353418933
Code
 raosudha89/clarification_question_generation_pytorch