Named Entity Correction in Neural Machine Translation Using the Attention Alignment Map

Jangwon Lee,Jungi Lee,Minho Lee,Gil-Jin Jang

doi:10.3390/app11157026

Jangwon Lee, Jungi Lee + Show 2 more

Open Access

https://doi.org/10.3390/app11157026

Copy DOI

Abstract

Neural machine translation (NMT) methods based on various artificial neural network models have shown remarkable performance in diverse tasks and have become mainstream for machine translation currently. Despite the recent successes of NMT applications, a predefined vocabulary is still required, meaning that it cannot cope with out-of-vocabulary (OOV) or rarely occurring words. In this paper, we propose a postprocessing method for correcting machine translation outputs using a named entity recognition (NER) model to overcome the problem of OOV words in NMT tasks. We use attention alignment mapping (AAM) between the named entities of input and output sentences, and mistranslated named entities are corrected using word look-up tables. The proposed method corrects named entities only, so it does not require retraining of existing NMT models. We carried out translation experiments on a Chinese-to-Korean translation task for Korean historical documents, and the evaluation results demonstrated that the proposed method improved the bilingual evaluation understudy (BLEU) score by 3.70 from the baseline.

Highlights

The surface form evaluates the ability of named entity recognition (NER) models to find rare entity words
The NER model used in the experiment was a two-stack long short-term memory (LSTM) model
Even the Neural machine translation (NMT) models that show state-of-the-art performance on multiple machine translation tasks are still limited when dealing with OOV and rarely occurring words

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Neural machine translation (NMT) models based on artificial neural networks have shown successful results in comparison to traditional machine translation methods [1,2,3,4,5]

Methods

Results

Discussion

Conclusion