首页|Findings from University of Mannheim Update Understanding of Machine Translation (Towards Explainable Evaluation Metrics for Machine Translation)

Findings from University of Mannheim Update Understanding of Machine Translation (Towards Explainable Evaluation Metrics for Machine Translation)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Translation is the subject of a report. According to news reporting originating in Mannheim, G ermany, by NewsRx journalists, research stated, “Unlike classical lexical overla p metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black -box large language models. They often achieve strong correlations with human judgments, but recent researc h indicates that the lower -quality classical metrics remain dominant, one of th e potential reasons being that their decision processes are more transparent.”

MannheimGermanyEuropeEmerging Tech nologiesMachine LearningMachine TranslationUniversity of Mannheim

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(MAY.17)