Neural-based machine translation for medical text domain. Based on European Medicines Agency leaflet texts

TL;DR

This paper explores neural machine translation for medical texts, specifically European Medicines Agency leaflets, comparing neural and statistical models to improve real-time Polish-English medical translation quality.

Contribution

It investigates the effects of different training methods on neural and statistical translation systems using medical domain data, with a focus on real-time translation performance.

Findings

Neural models show promising translation quality improvements.

Training methods significantly impact translation accuracy.

The system demonstrates potential for real-time medical translation applications.

Abstract

The quality of machine translation is rapidly evolving. Today one can find several machine translation systems on the web that provide reasonable translations, although the systems are not perfect. In some specific domains, the quality may decrease. A recently proposed approach to this domain is neural machine translation. It aims at building a jointly-tuned single neural network that maximizes translation performance, a very different approach from traditional statistical machine translation. Recently proposed neural machine translation models often belong to the encoder-decoder family in which a source sentence is encoded into a fixed length vector that is, in turn, decoded to generate a translation. The present research examines the effects of different training methods on a Polish-English Machine Translation system used for medical data. The European Medicines Agency parallel text corpus was used as the basis for training of neural and statistical network-based translation systems. The main machine translation evaluation metrics have also been used in analysis of the systems. A comparison and implementation of a real-time medical translator is the main focus of our experiments.