← Dictionary / BLEU score

BLEU score

Appears in 2 papers

Bilingual Evaluation Understudy.

As used in Paper 06 — Sequence to Sequence Learning with Neural Networks →

Bilingual Evaluation Understudy. The standard automated metric for

As used in Paper 07 — Neural Machine Translation by Jointly Learning to Align and Translate →

Bilingual Evaluation Understudy. The standard metric for machine translation quality, comparing a model's output to human-written reference translations. Ranges from 0 to 100; higher is better. The attention model improved BLEU by ~2 points on English-to-French, with larger gains on longer sentences.

Appears in papers

Paper 06 — Sequence to Sequence Learning with Neural Networks → Paper 07 — Neural Machine Translation by Jointly Learning to Align and Translate →