Uncertainty-Based Adaptive Learning for Reading Comprehension

Jing Wang, Jie Shen, Xiaofei Ma, Andrew Arnold

Keywords: machine reading comprehension, uncertainty-based sampling, adaptive loss minimization

Abstract: Recent years have witnessed a surge of successful applications of machine reading comprehension. Of central importance to the tasks is the availability of massive amount of labeled data, which facilitates the training of large-scale neural networks. However, in many real-world problems, annotated data are expensive to gather not only because of time cost and budget, but also of certain domain-specific restrictions such as privacy for healthcare data. In this regard, we propose an uncertainty-based adaptive learning algorithm for reading comprehension, which interleaves data annotation and model updating to mitigate the demand of labeling. Our key techniques are two-fold: 1) an unsupervised uncertainty-based sampling scheme that queries the labels of the most informative instances with respect to the currently learned model; and 2) an adaptive loss minimization paradigm that simultaneously fits the data and controls the degree of model updating. We demonstrate on the benchmark datasets that 25\% less labeled samples suffice to guarantee similar, or even improved performance. Our results demonstrate a strong evidence that for label-demanding scenarios, the proposed approach offers a practical guide on data collection and model training.

One-sentence Summary: We propose an uncertainty-based adaptive learning algorithm for reading comprehension, which interleaves data annotation and model updating to mitigate the demand of labeling.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=BelJUyyL8