Learning Word Subsumption Projections for the Russian Language / Ustalov Dmitry,Panchenko Alexander // . - 2016. - V. 8, l. .

ISSN/EISSN:
2271-2097 / нет данных
Type:
Proceedings Paper
Abstract:
The semantic relations of hypernymy and hyponymy are widely used in various natural language processing tasks for modelling the subsumptions in common sense reasoning. Since the popularisation of the distributional semantics, a significant attention is paid to applying word embeddings for inducing the relations between words. In this paper, we show our preliminary results on adopting the projection learning technique for computing hypernyms from hyponyms using word embeddings. We also conduct a series of experiments on the Russian language and release the open source software for learning hyponym-hypernym projections using both CPUs and GPUs, implemented with the TensorFlow machine learning framework.
Author keywords:
нет данных
DOI:
10.1051/itmconf/20160801006
Web of Science ID:
ISI:000392270800006
Соавторы в МНС:
Другие поля
Поле Значение
Editor Balk, I and Raigorodsky, A and Nikulchev, E
Booktitle INTERNATIONAL CONFERENCE ON BIG DATA AND ITS APPLICATIONS (ICBDA 2016)
Series ITM Web of Conferences
Note International Conference on Big Data and its Applications (ICBDA), Moscow, RUSSIA, SEP 19, 2016
Publisher E D P SCIENCES
Address 17 AVE DU HOGGAR PARC D ACTIVITES COUTABOEUF BP 112, F-91944 CEDEX A, FRANCE
Language English
Article-Number UNSP 01006
Research-Areas Automation \& Control Systems; Computer Science
Web-of-Science-Categories Automation \& Control Systems; Computer Science, Information Systems; Computer Science, Theory \& Methods
Author-Email dau@imm.uran.ru
ResearcherID-Numbers Ustalov, Dmitry/P-6307-2014
ORCID-Numbers Ustalov, Dmitry/0000-0002-9979-2188
Funding-Acknowledgement RFBR {[}16-37-00354 MOJI\_a]; Deutscher Akademischer Austauschdienst (DAAD) scholarship; Deutsche Forschungsgemeinschaft (DFG) foundation
Funding-Text The reported study was funded by RFBR according to the research project No. 16-37-00354 MOJI\_a. We are grateful to Nikolay Arefyev, Andrey Kutuzov, Andrey Krizhanovsky, Benjamin Milde and Alexander Bersenev for the fruitful discussions on the present study. Dmitry Ustalov was partially supported by the Deutscher Akademischer Austauschdienst (DAAD) scholarship. Alexander Panchenko was supported by the Deutsche Forschungsgemeinschaft (DFG) foundation under the project ``JOIN-T: Joining Ontologies and Semantics Induced from Text{''}.
Number-of-Cited-References 17
Usage-Count-Last-180-days 6
Usage-Count-Since-2013 6
Doc-Delivery-Number BG8HC