Erbs, Nicolai ; Santos, Pedro Bispo ; Zesch, Torsten ; Gurevych, Iryna (2015)
Counting What Counts: Decompounding for Keyphrase Extraction.
Beijing, China
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
A core assumption of keyphrase extraction is that a concept is more important if it is mentioned more often in a document. Especially in languages like German that form large noun compounds, frequency counts might be misleading as concepts “hidden” in compounds are not counted. We hypothesize that using decompounding before counting term frequencies may lead to better keyphrase extraction. We identified two effects of decompounding: (i) enhanced frequency counts, and (ii) more keyphrase candidates. We created two German evaluation datasets to test our hypothesis and analyzed the effect of additional decompounding for keyphrase extraction.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2015 |
| Autor(en): | Erbs, Nicolai ; Santos, Pedro Bispo ; Zesch, Torsten ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Counting What Counts: Decompounding for Keyphrase Extraction |
| Sprache: | Englisch |
| Publikationsjahr: | Juli 2015 |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of the ACL 2015 Workshop on Novel Computational Approaches to Keyphrase Extraction |
| Veranstaltungsort: | Beijing, China |
| URL / URN: | http://www.aclweb.org/anthology/W15-3603 |
| Kurzbeschreibung (Abstract): | A core assumption of keyphrase extraction is that a concept is more important if it is mentioned more often in a document. Especially in languages like German that form large noun compounds, frequency counts might be misleading as concepts “hidden” in compounds are not counted. We hypothesize that using decompounding before counting term frequencies may lead to better keyphrase extraction. We identified two effects of decompounding: (i) enhanced frequency counts, and (ii) more keyphrase candidates. We created two German evaluation datasets to test our hypothesis and analyzed the effect of additional decompounding for keyphrase extraction. |
| Freie Schlagworte: | UKP_p_WIKULU;UKP_p_DKPro;UKP_a_NLP4Wikis;UKP_reviewed;UKP_s_DKPro_Core |
| ID-Nummer: | TUD-CS-2015-0127 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum