A Template-based Method for Constrained Neural Machine Translation

TL;DR

This paper introduces a template-based approach for constrained neural machine translation that achieves high translation quality and accuracy with low latency, without altering the underlying NMT model architecture.

Contribution

It presents a novel template-based method that effectively incorporates constraints into NMT without modifying the model or decoding process.

Findings

Outperforms baseline methods in constrained translation tasks.

Maintains inference speed comparable to unconstrained NMT.

Achieves high translation quality and match accuracy.

Abstract

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models. Our basic idea is to rearrange the generation of constrained and unconstrained tokens through a template. Our method does not require any changes in the model architecture and the decoding algorithm. Experimental results show that the proposed template-based approach can outperform several representative baselines in both lexically and structurally constrained translation tasks.