An unsupervised word sense disambiguation system for under-resourced languages

Ustalov, Dmitry ; Teslenko, Denis ; Panchenko, Alexander ; Chernoskutov, Mikhail ; Biemann, Chris ; Ponzetto, Simone Paolo

URL:	http://www.lrec-conf.org/proceedings/lrec2018/summ...
Weitere URL:	https://arxiv.org/abs/1804.10686
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2018
Buchtitel:	LREC 2018, 11th International Conference on Language Resources and Evaluation : 7-12 May 2018, Miyazaki (Japan)
Seitenbereich:	1018-1022
Veranstaltungstitel:	International Conference on Language Resources and Evaluation 2018
Veranstaltungsort:	Miyazaki, Japan
Veranstaltungsdatum:	May 7-12, 2018
Herausgeber:	Calzolari, Nicoletta
Ort der Veröffentlichung:	Paris
Verlag:	European Language Resources Association, ELRA-ELDA
ISBN:	979-10-95546-00-9
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Fachgebiet:	004 Informatik
Freie Schlagwörter (Englisch):	word sense disambiguation , unsupervised learning , evaluation
Abstract:	In this paper, we present Mnogoznal, an unsupervised system for word sense disambiguation. Given a sentence, the system chooses the most relevant sense of each input word with respect to the semantic similarity between the given sentence and the synset constituting the sense of the target word. Mnogoznal has two modes of operation. The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context. The dense mode, instead, uses synset embeddings to cope with the sparsity problem. We describe the architecture of the present system and also conduct its evaluation on three different lexical semantic resources for Russian. We found that the dense mode substantially outperforms the sparse one on all datasets according to the adjusted Rand index.