Abstract : We observe that the precision and recall measures are not able to discriminate between very bad and slightly out of target alignments. We propose to generalise these measures by determining the distance between the obtained alignment and the expected one. This generalisation is done so that precision and recall results are at least preserved. In addition, the measures keep some tolerance to errors, i.e., accounting for some correspondences that are close to the target instead of out of target.
Type de document :
Communication dans un congrès
Proc. 4th ISWC poster session, Nov 2005, Galway, Ireland. No commercial editor., pp.PID-54, 2005, Proc. 4th ISWC poster session
https://hal.inria.fr/hal-00922280
Contributeur : Jérôme Euzenat
<>
Soumis le : mercredi 25 décembre 2013 - 19:35:37
Dernière modification le : vendredi 27 avril 2018 - 13:54:02
Document(s) archivé(s) le : mardi 25 mars 2014 - 22:11:54
Marc Ehrig, Jérôme Euzenat. Generalizing precision and recall for evaluating ontology matching. Proc. 4th ISWC poster session, Nov 2005, Galway, Ireland. No commercial editor., pp.PID-54, 2005, Proc. 4th ISWC poster session. 〈hal-00922280〉
