PRIM BLEU
An automatic evaluation metric for machine translation that measures the degree of lexical overlap between generated translations and reference translations based on n-gram precision.
Timeline (last 90 days)
Under the EasyOCR read-back protocol, FlowTranslator achieved an average PRIM BLEU of 20.6 and COMET of 57.2, significantly outperforming the strong trained baseline UniTranslator.
PRIM BLEU measures the degree of lexical overlap between the generated translation and the reference translation based on n-gram precision; a higher value indicates the translation is closer to the reference.
All Facts (2)
Under the EasyOCR read-back protocol, FlowTranslator achieved an average PRIM BLEU of 20.6 and COMET of 57.2, significantly outperforming the strong trained baseline UniTranslator.
50%UnverifiedPRIM BLEU measures the degree of lexical overlap between the generated translation and the reference translation based on n-gram precision; a higher value indicates the translation is closer to the reference.
50%