The Significance of Recall in Automatic Metrics Export

@misc{citeulike:904415, abstract = {Recent research has shown that a balanced harmonic mean (F1 measure) of unigram precision and recall outperforms the widely used BLEU and NIST metrics for Machine Translation evaluation in terms of correlation with human judgments of translation quality. We show that significantly better correlations can be achieved by placing more weight on recall than on precision. While this may seem unexpected, since BLEU and NIST focus on n-gram precision and disregard recall, our experiments show...}, author = {Evaluation, For M.}, citeulike-article-id = {904415}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.1630}, keywords = {mt-eval, recall}, posted-at = {2006-10-19 04:31:22}, priority = {0}, title = {The Significance of Recall in Automatic Metrics}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.1630} }

TY - GEN ID - citeulike:904415 L3 - citeulike-article-id:904415 N2 - Recent research has shown that a balanced harmonic mean (F1 measure) of unigram precision and recall outperforms the widely used BLEU and NIST metrics for Machine Translation evaluation in terms of correlation with human judgments of translation quality. We show that significantly better correlations can be achieved by placing more weight on recall than on precision. While this may seem unexpected, since BLEU and NIST focus on n-gram precision and disregard recall, our experiments show... TI - The Significance of Recall in Automatic Metrics KW - mt-eval KW - recall AU - Evaluation, For UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.1630 ER -