Název:	On continuous space word representations as input of LSTM language model
Autoři:	Soutner, Daniel Müller, Luděk
Citace zdrojového dokumentu:	SOUTNER, Daniel; MÜLLER, Luděk. On continuous space word representations as input of LSTM language model. In: Statistical Language and Speech Processing. Berlin: Springer, 2015, p. 267-274. (Lectures notes in computer science; 9449). ISBN 978-3-319-25788-4.
Datum vydání:	2015
Nakladatel:	Springer
Typ dokumentu:	článek article
URI:	http://hdl.handle.net/11025/26011
ISBN:	978-3-319-25788-4
ISSN:	0302-9743
Klíčová slova:	umělé neuronové sítě;modelování;kontinuální reprezentace slov
Klíčová slova v dalším jazyce:	artificial neural networks;modeling;continuous representations of words
Abstrakt v dalším jazyce:	Artificial neural networks have become the state-of-the-art in the task of language modelling whereas Long-Short Term Memory (LSTM) networks seem to be an efficient architecture. The continuous skip-gram and the continuous bag of words (CBOW) are algorithms for learning quality distributed vector representations that are able to capture a large number of syntactic and semantic word relationships. In this paper, we carried out experiments with a combination of these powerful models: the continuous representations of words trained with skip-gram/CBOW/GloVe method, word cache expressed as a vector using latent Dirichlet allocation (LDA). These all are used on the input of LSTM network instead of 1-of-N coding traditionally used in language models. The proposed models are tested on Penn Treebank and MALACH corpus.
Práva:	© Springer
Vyskytuje se v kolekcích:	Články / Articles (KKY)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.