Eintrag

Titel

Topic Modeling for Word Sense Induction

Personen

Johannes Knopp, Johanna Völker, Simone Paolo Ponzetto

Jahr

2013

Typ

Aufsatz

Verlag

Springer

Ort

Berlin, Heidelberg

Seiten

97 - 103

In

Language Processing and Knowledge in the Web. Proceedings of the 25th International GSCL Conference

Schlagwörter

Semantik
Topikalisierung

Abstract

In this paper, we present a novel approach to Word Sense Induction which is based on topic modeling. Key to our methodology is the use of word-topic distributions as a means to estimate sense distributions. We provide these distributions as input to a clustering algorithm in order to automatically distinguish between the senses of semantically ambiguous words. The results of our evaluation experiments indicate that the performance of our approach is comparable to state-of-the-art methods whose sense distinctions are not as easily interpretable.

https://grammis.ids-mannheim.de/bdg/80544