Regularization of Distinct Strategies for Unsupervised Question Generation

Junmo Kang, Giwon Hong, Haritz Puerto San Roman, Sung-Hyon Myaeng


Abstract
Unsupervised question answering (UQA) has been proposed to avoid the high cost of creating high-quality datasets for QA. One approach to UQA is to train a QA model with questions generated automatically. However, the generated questions are either too similar to a word sequence in the context or too drifted from the semantics of the context, thereby making it difficult to train a robust QA model. We propose a novel regularization method based on teacher-student architecture to avoid bias toward a particular question generation strategy and modulate the process of generating individual words when a question is generated. Our experiments demonstrate that we have achieved the goal of generating higher-quality questions for UQA across diverse QA datasets and tasks. We also show that this method can be useful for creating a QA model with few-shot learning.
Anthology ID:
2020.findings-emnlp.293
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3266–3277
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.293
DOI:
10.18653/v1/2020.findings-emnlp.293
Bibkey:
Cite (ACL):
Junmo Kang, Giwon Hong, Haritz Puerto San Roman, and Sung-Hyon Myaeng. 2020. Regularization of Distinct Strategies for Unsupervised Question Generation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3266–3277, Online. Association for Computational Linguistics.
Cite (Informal):
Regularization of Distinct Strategies for Unsupervised Question Generation (Kang et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2020.findings-emnlp.293.pdf
Code
 haritzpuerto/uqa
Data
HotpotQAMRQANatural QuestionsNewsQASQuADSearchQATriviaQA