{"_id":"69e4zT2BBbq2X3qXX","authorIDs":[],"author_short":["Haddoud, M.","Abdeddaim, S."],"bibbaseid":"haddoud-abdeddaim-accuratekeyphraseextractionbydiscriminatingoverlappingphrases-2014","bibdata":{"abstract":"In this paper we define the document phrase maximality index (DPM-index), a new measure to discriminate overlapping keyphrase candidates in a text document. As an application we developed a supervised learning system that uses 18 statistical features, among them the DPM-index and five other new features. We experimentally compared our results with those of 21 keyphrase extraction methods on SemEval-2010/Task-5 scientific articles corpus. When all the systems extract 10 keyphrases per document, our method enhances by 13% the F-score of the best system. In particular, the DPM-index feature increases the F-score of our keyphrase extraction system by a rate of 9%. This makes the DPM-index contribution comparable to that of the well-known TFIDF measure on such a system.","author":["Haddoud, Mounia","Abdeddaim, Said"],"author_short":["Haddoud, M.","Abdeddaim, S."],"bibtex":"@article{ haddoud_accurate_2014,\n title = {Accurate keyphrase extraction by discriminating overlapping phrases},\n url = {http://dx.doi.org/10.1177/0165551514530210},\n doi = {10.1177/0165551514530210},\n abstract = {In this paper we define the document phrase maximality index ({DPM}-index), a new measure to discriminate overlapping keyphrase candidates in a text document. As an application we developed a supervised learning system that uses 18 statistical features, among them the {DPM}-index and five other new features. We experimentally compared our results with those of 21 keyphrase extraction methods on {SemEval}-2010/Task-5 scientific articles corpus. When all the systems extract 10 keyphrases per document, our method enhances by 13% the F-score of the best system. In particular, the {DPM}-index feature increases the F-score of our keyphrase extraction system by a rate of 9%. This makes the {DPM}-index contribution comparable to that of the well-known {TFIDF} measure on such a system.},\n journal = {Journal of Information Science},\n author = {Haddoud, Mounia and Abdeddaim, Said},\n month = {April},\n year = {2014},\n keywords = {terminology_extraction}\n}","bibtype":"article","doi":"10.1177/0165551514530210","id":"haddoud_accurate_2014","journal":"Journal of Information Science","key":"haddoud_accurate_2014","keywords":"terminology_extraction","month":"April","title":"Accurate keyphrase extraction by discriminating overlapping phrases","type":"article","url":"http://dx.doi.org/10.1177/0165551514530210","year":"2014","bibbaseid":"haddoud-abdeddaim-accuratekeyphraseextractionbydiscriminatingoverlappingphrases-2014","role":"author","urls":{"Paper":"http://dx.doi.org/10.1177/0165551514530210"},"keyword":["terminology_extraction"],"downloads":0},"bibtype":"article","biburl":"http://bibbase.org/zotero/klaus.lepsky","creationDate":"2014-12-27T16:52:14.504Z","downloads":0,"keywords":["terminologieextraktion","terminology_extraction"],"search_terms":["accurate","keyphrase","extraction","discriminating","overlapping","phrases","haddoud","abdeddaim"],"title":"Accurate keyphrase extraction by discriminating overlapping phrases","year":2014,"dataSources":["toq45axpbC28psYaM"]}