Syntactic Knowledge via Graph Attention with BERT in Machine Translation

TL;DR

This paper introduces SGB, a method combining Graph Attention Networks and BERT to explicitly incorporate syntactic knowledge into machine translation, improving translation quality without reducing BLEU scores.

Contribution

The paper proposes a novel approach that jointly models syntactic dependencies with GAT and BERT, enhancing translation quality and interpretability in MT tasks.

Findings

SGB improves translation quality across multiple MT tasks.

Learning specific dependency relations correlates with better translation.

Syntax on the graph enhances syntactic modeling in BERT layers.

Abstract

Although the Transformer model can effectively acquire context features via a self-attention mechanism, deeper syntactic knowledge is still not effectively modeled. To alleviate the above problem, we propose Syntactic knowledge via Graph attention with BERT (SGB) in Machine Translation (MT) scenarios. Graph Attention Network (GAT) and BERT jointly represent syntactic dependency feature as explicit knowledge of the source language to enrich source language representations and guide target language generation. Our experiments use gold syntax-annotation sentences and Quality Estimation (QE) model to obtain interpretability of translation quality improvement regarding syntactic knowledge without being limited to a BLEU score. Experiments show that the proposed SGB engines improve translation quality across the three MT tasks without sacrificing BLEU scores. We investigate what length of source sentences benefits the most and what dependencies are better identified by the SGB engines. We also find that learning of specific dependency relations by GAT can be reflected in the translation quality containing such relations and that syntax on the graph leads to new modeling of syntactic aspects of source sentences in the middle and bottom layers of BERT.