SG-Net: Syntax-Guided Machine Reading Comprehension

TL;DR

This paper introduces SG-Net, a syntax-guided model that incorporates syntactic constraints into attention mechanisms to improve machine reading comprehension, demonstrating significant performance gains on benchmarks.

Contribution

The paper proposes a novel syntax-guided attention mechanism integrated into Transformer-based models for enhanced linguistic modeling in reading comprehension.

Findings

SG-Net improves performance on SQuAD 2.0 and RACE benchmarks.

Syntax-guided attention leads to more accurate focus on relevant words.

The approach outperforms baseline models without syntactic constraints.

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.