Publication Details

RNNLM - Recurrent Neural Network Language Modeling Toolkit

MIKOLOV, T.; KOMBRINK, S.; DEORAS, A.; BURGET, L.; ČERNOCKÝ, J. RNNLM - Recurrent Neural Network Language Modeling Toolkit. Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 1-4. ISBN: 978-1-4673-0366-8.
Czech title
RNNLM - Toolkit pro jazykové modelování pomocí rekurentních neuronových sítí
Type
conference paper
Language
English
Authors
Mikolov Tomáš, Ing., Ph.D.
Kombrink Stefan, Dipl.-Linguist.
Deoras Anoop
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
URL
Keywords

neural network, language modeling, speeech recognition

Abstract

This article is about the RNNLM - Recurrent Neural Network Language Modeling Toolkit, which was presented at the poster session of the ASRU 2011 conference.

Annotation

We present a freely available open-source toolkit for training recurrent neural network based language models. It can be easily used to improve existing speech recognition and machine translation systems. Also, it can be used as a baseline for future research of advanced language modeling techniques. In the paper, we discuss optimal parameter selection and different modes of functionality. The toolkit, example scripts and basic setups are freely available at http://rnnlm.sourceforge.net/.

Published
2011
Pages
1–4
Proceedings
Proceedings of ASRU 2011
ISBN
978-1-4673-0366-8
Publisher
IEEE Signal Processing Society
Place
Hilton Waikoloa Village, Big Island, Hawaii
BibTeX 
@inproceedings{BUT97008,
  author="Tomáš {Mikolov} and Stefan {Kombrink} and Anoop {Deoras} and Lukáš {Burget} and Jan {Černocký}",
  title="RNNLM - Recurrent Neural Network Language Modeling Toolkit",
  booktitle="Proceedings of ASRU 2011",
  year="2011",
  pages="1--4",
  publisher="IEEE Signal Processing Society",
  address="Hilton Waikoloa Village, Big Island, Hawaii",
  isbn="978-1-4673-0366-8",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/mikolov_asru2011_demo_RNNLM-1.pdf"
}
Back to top