Translationese in MT test sets biases evaluations, supporting exclusion of reverse-created data, re-evaluation of human-parity claims, and power analysis for reliable significance testing.
Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task. We empirically test this claim with alternative evaluation protocols, contrasting the evaluation of single sentences and entire documents. In a pairwise ranking experiment, human raters assessing adequacy and fluency show a stronger preference for human over machine translation when evaluating documents as compared to isolated sentences. Our findings emphasise the need to shift towards document-level evaluation as machine translation improves to the degree that errors which are hard or impossible to spot at the sentence-level become decisive in discriminating quality of different translation outputs.
verdicts
UNVERDICTED 2representative citing papers
A topic-modeling framework measures document-level thematic consistency in translations by aligning key tokens across languages with a bilingual dictionary and scoring via cosine similarity, providing explainable insights beyond sentence-level metrics.
citing papers explorer
-
Translationese in Machine Translation Evaluation
Translationese in MT test sets biases evaluations, supporting exclusion of reverse-created data, re-evaluation of human-parity claims, and power analysis for reliable significance testing.
-
An Explainable Approach to Document-level Translation Evaluation with Topic Modeling
A topic-modeling framework measures document-level thematic consistency in translations by aligning key tokens across languages with a bilingual dictionary and scoring via cosine similarity, providing explainable insights beyond sentence-level metrics.