Совместные метрики сегментного уровня WMT 2019
material
ID: wmt2019segmentlevelsharedmetrics
Related Papers
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
AbstractWe frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference. We propose training the paraphraser as …...