S³-NET: SRU-Based Sentence and Self-Matching Networks for Machine Reading Comprehension

Machine reading comprehension question answering (MRC-QA) is the task of understanding the context of a given passage to find a correct answer within it. A passage is composed of several sentences; therefore, the length of the input sentence becomes longer, leading to diminished performance. In this article, we propose S³-NET, which adds sentence-based encoding to solve this problem. S³-NET, which is based on a simple recurrent unit architecture, is a deep learning model that solves the MRC-QA by applying matching network to sentence-level encoding. In addition, S³-NET utilizes self-matching networks to compute attention weight for its own recurrent neural network sequences. We perform MRC-QA for the SQuAD dataset of English and MindsMRC dataset of Korean. The experimental results show that for SQuAD, the S³-NET model proposed in this article produces 71.91% and 74.12% exact match and 81.02% and 82.34% F1 in single and ensemble models, respectively, and for MindsMRC, our model achieves 69.43% and 71.28% exact match and 81.53% and 82.77% F1 in single and ensemble models, respectively.