RUSSE'2018 : a shared task on word sense induction for the Russian language

Panchenko, Alexander ; Lopukhina, Anastasiya ; Ustalov, Dmitry ; Lopukhin, Konstantin ; Arefyev, Nikolay ; Leontyev, Alexey ; Loukachevitch, Natalia

Vorschau

PDF
RUSSE'18 Shared Task Paper.pdf - Veröffentlichte Version
Download (324kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/44299
Weitere URL:	http://www.dialog-21.ru/media/4280/dialog2018scopu...
URN:	urn:nbn:de:bsz:180-madoc-442992
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2018
Buchtitel:	Computational Linguistics and Intellectual Technologies : Papers from the Annual conference "Dialogue" 2018 : 24th International Conference on Computational Linguistics and Intellectual Technologies, May 30 - June 2, 2018 Moscow
Titel einer Zeitschrift oder einer Reihe:	Dialogue
Band/Volume:	17
Seitenbereich:	547-564
Veranstaltungstitel:	24rd International Conference on Computational Linguistics and Intellectual Technologies 2018
Veranstaltungsort:	Moscow, Russia
Veranstaltungsdatum:	May 30-June 2, 2018
Ort der Veröffentlichung:	Moscow, Russia
Verlag:	RSUH
ISSN:	2221-7932 , 2075-7182
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	004 Informatik 400 Sprache, Linguistik
Freie Schlagwörter (Englisch):	lexical semantics , word sense induction , word sense disambiguation , polysemy , homonymy
Abstract:	The paper describes the results of the first shared task on word sense induction (WSI) for the Russian language. While similar shared tasks were conducted in the past for some Romance and Germanic languages, we explore the performance of sense induction and disambiguation methods for a Slavic language that shares many features with other Slavic languages, such as rich morphology and free word order. The participants were asked to group contexts with a given word in accordance with its senses that were not provided beforehand. For instance, given a word “bank” and a set of contexts with this word, e.g. “bank is a financial institution that accepts deposits” and “river bank is a slope beside a body of water”, a participant was asked to cluster such contexts in the unknown in advance number of clusters corresponding to, in this case, the “company” and the “area” senses of the word “bank”. For the purpose of this evaluation campaign, we developed three new evaluation datasets based on sense inventories that have different sense granularity. The contexts in these datasets were sampled from texts of Wikipedia, the academic corpus of Russian, and an explanatory dictionary of Russian. Overall 18 teams participated in the competition submitting 383 models. Multiple teams managed to substantially outperform competitive state-of-the-art baselines from the previous years based on sense embeddings.