ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback

TL;DR

ChrEnTranslate is an online Cherokee-English translation system that combines statistical and neural models, quality estimation, and user feedback to improve translation accuracy and facilitate human-in-the-loop learning for endangered language preservation.

Contribution

It introduces a comprehensive translation demo with quality estimation and feedback interfaces, demonstrating state-of-the-art performance and exploring human-in-the-loop training for Cherokee-English translation.

Findings

State-of-the-art translation performance achieved.

Quality estimation correlates well with BLEU and human judgment.

Adding expert feedback improves model performance.

Abstract

We introduce ChrEnTranslate, an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as provides quality estimation to inform users of reliability, two user feedback interfaces for experts and common users respectively, example inputs to collect human translations for monolingual data, word alignment visualization, and relevant terms from the Cherokee-English dictionary. The quantitative evaluation demonstrates that our backbone translation models achieve state-of-the-art translation performance and our quality estimation well correlates with both BLEU and human judgment. By analyzing 216 pieces of expert feedback, we find that NMT is preferable because it copies less than SMT, and, in general, current models can translate fragments of the source sentence but make major mistakes. When we add these 216 expert-corrected parallel texts back into the training set and retrain models, equal or slightly better performance is observed, which indicates the potential of human-in-the-loop learning. Our online demo is at https://chren.cs.unc.edu/ , our code is open-sourced at https://github.com/ZhangShiyue/ChrEnTranslate , and our data is available at https://github.com/ZhangShiyue/ChrEn