Briefly, what do BLEU and ROUGE measure?
mediumAnswer
- BLEU: n-gram precision of the generated hypothesis against one or more reference translations, with a brevity penalty for short outputs.
- Standard for machine translation.
- ROUGE: n-gram recall of the summary against reference summaries (ROUGE-N for n-grams, ROUGE-L for longest common subsequence).
- Standard for summarization.
- Both are crude — modern metrics use learned embeddings (BERTScore, BLEURT, COMET) or LLM-as-judge.
Check yourself — multiple choice
- BLEU is recall, ROUGE is precision
- BLEU = n-gram precision (MT), ROUGE = n-gram recall (summarization); modern metrics use embeddings
- Both measure loss
- BLEU is a training objective
BLEU: precision (MT); ROUGE: recall (summarization); modern: BERTScore/COMET/LLM-judge.
#transformers#losses
Practise Deep Learning
214 interview questions in this topic.
Related questions
- How does self-attention work in a transformer?
- Why does a transformer need positional encoding?
- Why did transformers replace RNNs for sequence modeling?
- What are SiLU (Swish) and GELU, and why do transformers prefer them over ReLU?
- Why compute softmax + cross-entropy jointly via log-sum-exp?
- How should the output head be designed for a regression task with a strictly positive target?