An Effective Method using Phrase Mechanism in Neural Machine Translation

TL;DR

This paper introduces PhraseTransformer, a phrase mechanism integrated into Transformer models, significantly enhancing neural machine translation quality for Vietnamese-Chinese with notable BLEU score improvements.

Contribution

The paper presents a novel phrase mechanism, PhraseTransformer, that improves Transformer-based NMT systems specifically for Vietnamese-Chinese translation tasks.

Findings

Achieved BLEU scores of 35.3 for Vietnamese to Chinese

Achieved BLEU scores of 33.2 for Chinese to Vietnamese

Demonstrated effectiveness of phrase mechanism in NMT

Abstract

Machine Translation is one of the essential tasks in Natural Language Processing (NLP), which has massive applications in real life as well as contributing to other tasks in the NLP research community. Recently, Transformer -based methods have attracted numerous researchers in this domain and achieved state-of-the-art results in most of the pair languages. In this paper, we report an effective method using a phrase mechanism, PhraseTransformer, to improve the strong baseline model Transformer in constructing a Neural Machine Translation (NMT) system for parallel corpora Vietnamese-Chinese. Our experiments on the MT dataset of the VLSP 2022 competition achieved the BLEU score of 35.3 on Vietnamese to Chinese and 33.2 BLEU scores on Chinese to Vietnamese data. Our code is available at https://github.com/phuongnm94/PhraseTransformer.