BLEU score: 30.78
Papers with Code · CC BY-SA 4.0
Machine Translation
Machine translation is the task of translating a sentence in a source language to a different target language.
Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.
One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.
<span style="color:grey; opacity: 0.6">( Image credit: Google seq2seq )</span>
논문
BLEU score: 29.57
BLEU score: 31.26
BLEU score: 30.7
BLEU score: 30.07Hardware Burden: 24G
BLEU score: 32.1Number of Params: 11110M
BLEU score: 29.6
BLEU score: 29.11
BLEU score: 29.52
BLEU score: 30.75
BLEU score: 29.7
BLEU score: 29.2
BLEU score: 30.4Number of Params: 215M
BLEU score: 29.2
BLEU score: 29.9
BLEU score: 29.8
BLEU score: 29.56Number of Params: 68M
BLEU score: 29.7Number of Params: 213M
BLEU score: 30.1
BLEU score: 30.91Hardware Burden: 49G
BLEU score: 33.89SacreBLEU: 32.35
BLEU score: 29.3Number of Params: 210MHardware Burden: 9G
BLEU score: 29.2
BLEU score: 29.3
BLEU score: 29.21
BLEU score: 29.8SacreBLEU: 29.2Number of Params: 218M
BLEU score: 29.6Number of Params: 209M
BLEU score: 35.0SacreBLEU: 33.8Hardware Burden: 146G
BLEU score: 30.1SacreBLEU: 29.5Number of Params: 256M