TU Darmstadt / ULB / TUbiblio

Discovering Links Using Semantic Relatedness

Hoffart, Johannes ; Bär, Daniel ; Zesch, Torsten ; Gurevych, Iryna
Hrsg.: Geva, Shlomo ; Kamps, Jaap ; Trotman, Andrew (2009)
Discovering Links Using Semantic Relatedness.
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

We present our approaches for link discovery in document collections with or without existing links. In collections containing links, we discover links using measures of link anchor ranking based on existing links. In collections without links, we gather noun phrases as anchor candidates. To discover targets, we use a measure of semantic relatedness between texts. We find that semantic relatedness is useful to identify targets for ambiguous link anchors. In collections that contain no existing links, using only document titles as anchor candidates can be enhanced by using arbitrary noun phrases extracted from documents.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2009
Herausgeber: Geva, Shlomo ; Kamps, Jaap ; Trotman, Andrew
Autor(en): Hoffart, Johannes ; Bär, Daniel ; Zesch, Torsten ; Gurevych, Iryna
Art des Eintrags: Bibliographie
Titel: Discovering Links Using Semantic Relatedness
Sprache: Englisch
Publikationsjahr: Dezember 2009
Buchtitel: INEX 2009 Workshop Preproceedings
URL / URN: http://www.inex.otago.ac.nz/data/proceedings/INEX2009-prepro...
Kurzbeschreibung (Abstract):

We present our approaches for link discovery in document collections with or without existing links. In collections containing links, we discover links using measures of link anchor ranking based on existing links. In collections without links, we gather noun phrases as anchor candidates. To discover targets, we use a measure of semantic relatedness between texts. We find that semantic relatedness is useful to identify targets for ambiguous link anchors. In collections that contain no existing links, using only document titles as anchor candidates can be enhanced by using arbitrary noun phrases extracted from documents.

Freie Schlagworte: UKP_a_NLP4Wikis;UKP_p_WIKULU;UKP_s_DKPro_Similarity
ID-Nummer: TUD-CS-2010-0009
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 Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen