Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data Augmentation

Arda Tezcan,Bram Vanroy,Bram Bulté

doi:10.3390/informatics8010007

Abstract

We identify a number of aspects that can boost the performance of Neural Fuzzy Repair (NFR), an easy-to-implement method to integrate translation memory matches and neural machine translation (NMT). We explore various ways of maximising the added value of retrieved matches within the NFR paradigm for eight language combinations, using Transformer NMT systems. In particular, we test the impact of different fuzzy matching techniques, sub-word-level segmentation methods and alignment-based features on overall translation quality. Furthermore, we propose a fuzzy match combination technique that aims to maximise the coverage of source words. This is supplemented with an analysis of how translation quality is affected by input sentence length and fuzzy match score. The results show that applying a combination of the tested modifications leads to a significant increase in estimated translation quality over all baselines for all language combinations.

Highlights

Recent advances in machine translation (MT), most notably linked to the introduction of deep neural networks in combination with large data sets and matching computational capacity [1], have resulted in a significant increase in the quality of MT output, especially for specialised, technical and/or domain-specific translations [2]
We focus on TMbased data augmentation methods within the neural machine translation (NMT) framework (Section 2.3), the approach that is followed in this paper
We identified a number of adaptations that can further improve the quality of the MT output generated by the neural fuzzy repair (NFR) systems: retrieving fuzzy matches using cosine similarity for sentence embeddings obtained on the basis of sub-word units, adding features based on alignment information, and increasing the informativeness of retrieved matches by maximising source sentence coverage

Summary

Introduction

Recent advances in machine translation (MT), most notably linked to the introduction of deep neural networks in combination with large data sets and matching computational capacity [1], have resulted in a significant increase in the quality of MT output, especially for specialised, technical and/or domain-specific translations [2]. The increase in quality has been such that more and more professional translators, translation services, and language service providers have integrated MT systems in their workflows [3]. MT tends to be used as a ‘back-off’ solution to TMs in cases where no sufficiently similar source sentence is found in the TM [12,13], since post-editing MT output in many cases takes more time than correcting (close) TM matches. This is, for example, due to inconsistencies in translation and a lack of overlap between MT output and the desired translation [14]. The perception of translators is that MT errors are often not predictable or coherent, which results in a lower confidence for MT output in comparison to TM segments [14,17]

Objectives

Methods

Results

Discussion

Conclusion