TranslationCorrect: A Unified Framework for Machine Translation Post-Editing with Predictive Error Assistance

TL;DR

TranslationCorrect is an integrated framework that streamlines machine translation post-editing and research data collection by combining error prediction, translation, and annotation in a user-friendly environment, improving efficiency and satisfaction.

Contribution

It introduces a unified platform that combines MT generation, error prediction, and annotation, with a user-centered design validated by user studies, enhancing workflow efficiency.

Findings

Significantly improves translation efficiency.

Enhances user satisfaction in post-editing tasks.

Exports high-quality annotations compatible with error detection models.

Abstract

Machine translation (MT) post-editing and research data collection often rely on inefficient, disconnected workflows. We introduce TranslationCorrect, an integrated framework designed to streamline these tasks. TranslationCorrect combines MT generation using models like NLLB, automated error prediction using models like XCOMET or LLM APIs (providing detailed reasoning), and an intuitive post-editing interface within a single environment. Built with human-computer interaction (HCI) principles in mind to minimize cognitive load, as confirmed by a user study. For translators, it enables them to correct errors and batch translate efficiently. For researchers, TranslationCorrect exports high-quality span-based annotations in the Error Span Annotation (ESA) format, using an error taxonomy inspired by Multidimensional Quality Metrics (MQM). These outputs are compatible with state-of-the-art error detection models and suitable for training MT or post-editing systems. Our user study confirms that TranslationCorrect significantly improves translation efficiency and user satisfaction over traditional annotation methods.