A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
This work addresses a bottleneck in training evidence extractors for MRC, particularly in tasks like YES/NO and multi-choice QA, offering a practical solution for researchers and practitioners in natural language processing.
The paper tackles the problem of expensive evidence labels in non-extractive machine reading comprehension tasks by proposing a self-training method that generates pseudo evidence labels iteratively, achieving improvements on seven datasets across three MRC tasks.
Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor. The former seeks the most relevant information from a reference text, while the latter is to locate or generate answers from the extracted evidence. Despite the importance of evidence labels for training the evidence extractor, they are not cheaply accessible, particularly in many non-extractive MRC tasks such as YES/NO question answering and multi-choice MRC. To address this problem, we present a Self-Training method (STM), which supervises the evidence extractor with auto-generated evidence labels in an iterative process. At each iteration, a base MRC model is trained with golden answers and noisy evidence labels. The trained model will predict pseudo evidence labels as extra supervision in the next iteration. We evaluate STM on seven datasets over three MRC tasks. Experimental results demonstrate the improvement on existing MRC models, and we also analyze how and why such a self-training method works in MRC. The source code can be obtained from https://github.com/SparkJiao/Self-Training-MRC