Cluster Labeling by Word Embeddings and WordNet’s Hypernymy

Poostchi, H; Piccardi, M

Cluster Labeling by Word Embeddings and WordNet’s Hypernymy

Poostchi, H

Piccardi, M

Permalink

Publication Type:: Conference Proceeding
Citation:: https://www.aclweb.org/anthology/U18-1, 2018
Issue Date:: 2018-12-15

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript versionAdobe PDF (254.72 kB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Poostchi, H https://orcid.org/0000-0002-8725-2619	en_US
dc.contributor.author	Piccardi, M https://orcid.org/0000-0001-9250-6604	en_US
dc.date	2018-12-10	en_US
dc.date.available	2018-11-10	en_US
dc.date.issued	2018-12-15	en_US
dc.identifier.citation	https://www.aclweb.org/anthology/U18-1, 2018	en_US
dc.identifier.issn	1834-7037	en_US
dc.identifier.uri	http://hdl.handle.net/10453/132471
dc.description.abstract	Cluster labeling is the assignment of representative labels to clusters of documents or words. Once assigned, the labels can play an important role in applications such as navigation, search and document classification. However, finding appropriately descriptive labels is still a challenging task. In this paper, we propose various approaches for assigning labels to word clusters by leveraging word embeddings and the synonymy and hypernymy relations in the WordNet lexical ontology. Experiments carried out using the WebAP document dataset have shown that one of the approaches stand out in the comparison and is capable of selecting labels that are reasonably aligned with those chosen by a pool of four human annotators.	en_US
dc.relation.ispartof	https://www.aclweb.org/anthology/U18-1	en_US
dc.relation.ispartof	Annual Workshop of The Australasian Language Technology Association	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Cluster Labeling by Word Embeddings and WordNet’s Hypernymy	en_US
dc.type	Conference Proceeding
utslib.location.activity	Dunedin, New Zealand	en_US
utslib.for	0806 Information Systems	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
utslib.copyright.status	open_access	*
pubs.consider-herdc	true	en_US
pubs.finish-date	2018-12-12	en_US
pubs.publication-status	Published	en_US
pubs.start-date	2018-12-10	en_US

Abstract:

Cluster labeling is the assignment of representative labels to clusters of documents or words. Once assigned, the labels can play an important role in applications such as navigation, search and document classification. However, finding appropriately descriptive labels is still a challenging task. In this paper, we propose various approaches for assigning labels to word clusters by leveraging word embeddings and the synonymy and hypernymy relations in the WordNet lexical ontology. Experiments carried out using the WebAP document dataset have shown that one of the approaches stand out in the comparison and is capable of selecting labels that are reasonably aligned with those chosen by a pool of four human annotators.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/128708