Cooperative Semi-Supervised Transfer Learning of Machine Reading Comprehension

Anonymous

Abstract: Pretrained language models have significantly improved the performance of down-stream 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-play learning framework, REGEX, for automatically generating more non-trivial question-answer pairs to improve model performance. REGEX 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 reinforcement learning technique to reward generating high-quality questions and to improve the answer extraction model's performance. Experiment results show that REGEX 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.