Conference paper

OTRUSINA Lubomír and SMRŽ Pavel. Deep Learning from Web-Scale Corpora for Better Dictionary Interfaces. In: Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex). Dublin: Association for Computational Linguistics, 2014, pp. 22-30. ISBN 978-1-63439-217-4. Available from: http://www.aclweb.org/anthology/W/W14/W14-4703.pdf
Publication language:english
Original title:Deep Learning from Web-Scale Corpora for Better Dictionary Interfaces
Title (cs):Deep Learning z webových korpusů pro lepší rozhraní ke slovníkům
Pages:22-30
Proceedings:Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex)
Conference:workshop Cogalex 2014, conference Coling 2014
Place:Dublin, IE
Year:2014
URL:http://www.aclweb.org/anthology/W/W14/W14-4703.pdf
ISBN:978-1-63439-217-4
Publisher:Association for Computational Linguistics
Keywords
Word2Vec, neural networks, ClueWeb, UKWaC, tip-of-the-tongue phenomenon
Annotation
This paper explores advanced learning mechanisms - neural networks trained by the Word2Vec method - for predicting word associations. We discuss how the approach can be built into dictionary interfaces to help tip-of-the-tongue searches. We also describe our contribution to the CogALex 2014 shared task. We argue that the reverse response-stimulus word associations chosen for the shared task are only mildly related to the motivation idea of the lexical access support system. The methods employed in our contribution are briefly introduced. We present results of experiments with various parameter settings and show what improvement can be expected if more than one answer is allowed. The paper concludes with a proposal for a new collective effort to assemble real tip-of-the-tongue situation records for future, more-realistic evaluations.
BibTeX:
@INPROCEEDINGS{
   author = {Lubom{\'{i}}r Otrusina and Pavel Smr{\v{z}}},
   title = {Deep Learning from Web-Scale Corpora for Better Dictionary
	Interfaces},
   pages = {22--30},
   booktitle = {Proceedings of the 4th Workshop on Cognitive Aspects of the
	Lexicon (CogALex)},
   year = {2014},
   location = {Dublin, IE},
   publisher = {Association for Computational Linguistics},
   ISBN = {978-1-63439-217-4},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10709}
}

Your IPv4 address: 54.242.205.33
Switch to IPv6 connection

DNSSEC [dnssec]