Evaluation of Machine Translation and its Evaluation Export

@inproceedings{citeulike:904414, abstract = {Evaluation of MT evaluation measures is limited by inconsistent human judgment data. Nonetheless, machine translation can be evaluated using the well-known measures precision, recall, and the F-measure. The F-measure has significantly higher correlation with human judgments than recently proposed alternatives. More importantly, the standard measures have an intuitive graphical interpretation, which can facilitate insight into how MT systems might be improved. The relevant software is publicly...}, author = {Turian, Joseph P. and Shen, Luke and Melamed, Dan I.}, booktitle = {Machine Translation Summit IX}, citeulike-article-id = {904414}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.388}, keywords = {mt-eval}, month = {September}, organization = {International Association for Machine Translation}, posted-at = {2006-10-19 04:29:56}, priority = {3}, title = {Evaluation of Machine Translation and its Evaluation}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.388}, year = {2003} }

TY - CONF ID - citeulike:904414 L3 - citeulike-article-id:904414 N2 - Evaluation of MT evaluation measures is limited by inconsistent human judgment data. Nonetheless, machine translation can be evaluated using the well-known measures precision, recall, and the F-measure. The F-measure has significantly higher correlation with human judgments than recently proposed alternatives. More importantly, the standard measures have an intuitive graphical interpretation, which can facilitate insight into how MT systems might be improved. The relevant software is publicly... OR - International Association for Machine Translation TI - Evaluation of Machine Translation and its Evaluation T2 - Machine Translation Summit IX KW - mt-eval AU - Turian, Joseph AU - Shen, Luke AU - Melamed, Dan PY - 2003/September// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.388 ER -