On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms

TL;DR

This paper identifies a gap in machine translation for technical acronyms, proposing an enhanced workflow with an acronym corpus and a search-based disambiguation method that improves translation accuracy.

Contribution

It introduces a new acronym corpus and a search-based thresholding algorithm to improve acronym translation in machine translation systems.

Findings

Acronym translation errors can reach up to 50% in current systems.

The proposed method improves accuracy by nearly 10% over Google Translate and OpusMT.

The workflow enhances the handling of technical terms in machine translation.

Abstract

The typical workflow for a professional translator to translate a document from its source language (SL) to a target language (TL) is not always focused on what many language models in natural language processing (NLP) do - predict the next word in a series of words. While high-resource languages like English and French are reported to achieve near human parity using common metrics for measurement such as BLEU and COMET, we find that an important step is being missed: the translation of technical terms, specifically acronyms. Some state-of-the art machine translation systems like Google Translate which are publicly available can be erroneous when dealing with acronyms - as much as 50% in our findings. This article addresses acronym disambiguation for MT systems by proposing an additional step to the SL-TL (FR-EN) translation workflow where we first offer a new acronym corpus for public consumption and then experiment with a search-based thresholding algorithm that achieves nearly 10% increase when compared to Google Translate and OpusMT.