SG-Net: Syntax-Guided Machine Reading Comprehension

Authors

  • Zhuosheng Zhang Shanghai Jiao Tong University
  • Yuwei Wu Shanghai Jiao Tong University
  • Junru Zhou Shanghai Jiao Tong University
  • Sufeng Duan Shanghai Jiao Tong University
  • Hai Zhao Shanghai Jiao Tong University
  • Rui Wang National Institute of Information and Communications Technology

DOI:

https://doi.org/10.1609/aaai.v34i05.6511

Abstract

For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanism for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. To verify its effectiveness, the proposed SG-Net is applied to typical pre-trained language model BERT which is right based on a Transformer encoder. Extensive experiments on popular benchmarks including SQuAD 2.0 and RACE show that the proposed SG-Net design helps achieve substantial performance improvement over strong baselines.

Downloads

Published

2020-04-03

How to Cite

Zhang, Z., Wu, Y., Zhou, J., Duan, S., Zhao, H., & Wang, R. (2020). SG-Net: Syntax-Guided Machine Reading Comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9636-9643. https://doi.org/10.1609/aaai.v34i05.6511

Issue

Section

AAAI Technical Track: Natural Language Processing