MAP (mean average precision) measures: area under the precision-recall curve averaged across queries

BLEU vs ROUGE: BLEU measures precision of n-grams, ROUGE measures recall

BLEU measures precision of n-grams, ROUGE measures recall

to normalize features: when features have different scales and you use distance-based methods

Why do some things need to be adjusted to compare fairly?

Receiver operating characteristic

Ever wondered how doctors decide if a test really finds cancer?

Precision and recall

Precision = Relevant retrieved instances / All retrieved instances

word error rate (WER) measures: edit distance between predicted and reference transcriptions

WER measures the percentage of errors in transcription

Euclidean geometry

Euclidean distance measures absolute position in space