TU Darmstadt / ULB / TUbiblio

A Language-independent Sense Clustering Approach for Enhanced WSD

Matuschek, Michael and Miller, Tristan and Gurevych, Iryna
Ruppenhofer, Josef and Faaß, Gertrud (eds.) (2014):
A Language-independent Sense Clustering Approach for Enhanced WSD.
In: Proceedings of the 12th Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2014), Universitätsverlag Hildesheim, Hildesheim, Germany, ISBN 978-3-934105-46-1,
[Online-Edition: https://fileserver.ukp.informatik.tu-darmstadt.de/UKP_Webpag...],
[Conference or Workshop Item]

Abstract

We present a method for clustering word senses of a lexical-semantic resource by mapping them to those of another sense inventory. This is a promising way of reducing polysemy in sense inventories and consequently improving word sense disambiguation performance. In contrast to previous approaches, we use Dijkstra-WSA, a parameterizable alignment algorithm which is largely resource- and language-agnostic. To demonstrate this, we apply our technique to GermaNet, the German equivalent to WordNet. The GermaNet sense clusterings we induce through alignments to various collaboratively constructed resources achieve a significant boost in accuracy, even though our method is far less complex and less dependent on language-specific knowledge than past approaches.

Item Type: Conference or Workshop Item
Erschienen: 2014
Editors: Ruppenhofer, Josef and Faaß, Gertrud
Creators: Matuschek, Michael and Miller, Tristan and Gurevych, Iryna
Title: A Language-independent Sense Clustering Approach for Enhanced WSD
Language: English
Abstract:

We present a method for clustering word senses of a lexical-semantic resource by mapping them to those of another sense inventory. This is a promising way of reducing polysemy in sense inventories and consequently improving word sense disambiguation performance. In contrast to previous approaches, we use Dijkstra-WSA, a parameterizable alignment algorithm which is largely resource- and language-agnostic. To demonstrate this, we apply our technique to GermaNet, the German equivalent to WordNet. The GermaNet sense clusterings we induce through alignments to various collaboratively constructed resources achieve a significant boost in accuracy, even though our method is far less complex and less dependent on language-specific knowledge than past approaches.

Title of Book: Proceedings of the 12th Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2014)
Publisher: Universitätsverlag Hildesheim
ISBN: 978-3-934105-46-1
Uncontrolled Keywords: reviewed;UKP_a_LangTech4eHum
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Hildesheim, Germany
Date Deposited: 31 Dec 2016 14:29
Official URL: https://fileserver.ukp.informatik.tu-darmstadt.de/UKP_Webpag...
Identification Number: TUD-CS-2014-0878
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item