A New NMT Model for Translating Clinical Texts from English to Spanish

TL;DR

This paper introduces NOOV, a neural machine translation model designed to improve English-Spanish clinical text translation by effectively handling unknown words and leveraging biomedical resources, with minimal in-domain data.

Contribution

The paper presents NOOV, a novel NMT system that combines learned bilingual lexicons and biomedical phrase look-up tables to address unknown words and improve translation quality in clinical texts.

Findings

NOOV outperforms baseline models in accuracy and fluency.

It effectively handles unknown words with minimal in-domain data.

The system enhances phrase generation in clinical translation tasks.

Abstract

Translating electronic health record (EHR) narratives from English to Spanish is a clinically important yet challenging task due to the lack of a parallel-aligned corpus and the abundant unknown words contained. To address such challenges, we propose \textbf{NOOV} (for No OOV), a new neural machine translation (NMT) system that requires little in-domain parallel-aligned corpus for training. NOOV integrates a bilingual lexicon automatically learned from parallel-aligned corpora and a phrase look-up table extracted from a large biomedical knowledge resource, to alleviate both the unknown word problem and the word-repeat challenge in NMT, enhancing better phrase generation of NMT systems. Evaluation shows that NOOV is able to generate better translation of EHR with improvement in both accuracy and fluency.