QainfoMax: Learning robust question answering system by mutual information maximization
Journal
EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Pages
3370-3375
Date Issued
2020
Author(s)
Yeh, Y.-T.
Abstract
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but do not actually answer the question. To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. QAInfomax helps regularize the model to not simply learn the superficial correlation for answering questions. The experiments show that our proposed QAInfomax achieves the state-of-the-art performance on the benchmark Adversarial-SQuAD dataset. © 2019 Association for Computational Linguistics
Other Subjects
Benchmarking; Existing systems; Mutual information maximization; Mutual informations; Question Answering; Question answering systems; Reading comprehension; Regularizer; State-of-the-art performance; Natural language processing systems
Type
conference paper