Cooperative Self-training of Machine Reading Comprehension

Hongyin Luo, Shang-Wen Li, Mingye Gao, Seunghak Yu, James Glass


Abstract
Pretrained language models have significantly improved the performance of downstream language understanding tasks, including extractive question answering, by providing high-quality contextualized word embeddings. However, training question answering models still requires large amounts of annotated data for specific domains. In this work, we propose a cooperative self-training framework, RGX, for automatically generating more non-trivial question-answer pairs to improve model performance. RGX is built upon a masked answer extraction task with an interactive learning environment containing an answer entity Recognizer, a question Generator, and an answer eXtractor. Given a passage with a masked entity, the generator generates a question around the entity, and the extractor is trained to extract the masked entity with the generated question and raw texts. The framework allows the training of question generation and answering models on any text corpora without annotation. We further leverage a self-training technique to improve the performance of both question generation and answer extraction models. Experiment results show that RGX outperforms the state-of-the-art (SOTA) pretrained language models and transfer learning approaches on standard question-answering benchmarks, and yields the new SOTA performance under given model size and transfer learning settings.
Anthology ID:
2022.naacl-main.18
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
244–257
Language:
URL:
https://aclanthology.org/2022.naacl-main.18
DOI:
10.18653/v1/2022.naacl-main.18
Bibkey:
Cite (ACL):
Hongyin Luo, Shang-Wen Li, Mingye Gao, Seunghak Yu, and James Glass. 2022. Cooperative Self-training of Machine Reading Comprehension. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 244–257, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Cooperative Self-training of Machine Reading Comprehension (Luo et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.18.pdf
Code
 luohongyin/RGX
Data
AdversarialQAMRQANatural QuestionsSQuAD