Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

Siddhant Garg, Alessandro Moschitti


Abstract
In this paper we propose a novel approach towards improving the efficiency of Question Answering (QA) systems by filtering out questions that will not be answered by them. This is based on an interesting new finding: the answer confidence scores of state-of-the-art QA systems can be approximated well by models solely using the input question text. This enables preemptive filtering of questions that are not answered by the system due to their answer confidence scores being lower than the system threshold. Specifically, we learn Transformer-based question models by distilling Transformer-based answering models. Our experiments on three popular QA datasets and one industrial QA benchmark demonstrate the ability of our question models to approximate the Precision/Recall curves of the target QA system well. These question models, when used as filters, can effectively trade off lower computation cost of QA systems for lower Recall, e.g., reducing computation by ~60%, while only losing ~3-4% of Recall.
Anthology ID:
2021.emnlp-main.583
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7329–7346
Language:
URL:
https://aclanthology.org/2021.emnlp-main.583
DOI:
10.18653/v1/2021.emnlp-main.583
Bibkey:
Cite (ACL):
Siddhant Garg and Alessandro Moschitti. 2021. Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7329–7346, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering (Garg & Moschitti, EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.583.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.583.mp4
Data
ASNQNatural QuestionsParalexSQuADWikiQA