Publication Details

Strategies for Training Large Scale Neural Network Language Models

MIKOLOV Tomáš, DEORAS Anoop, POVEY Daniel, BURGET Lukáš and ČERNOCKÝ Jan. Strategies for Training Large Scale Neural Network Language Models. In: Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011, pp. 196-201. ISBN 978-1-4673-0366-8.
Czech title
Strategie pro trénování velkých jazykových modelů založených na neuronových sítích
Type
conference paper
Language
english
Authors
Mikolov Tomáš, Ing. (DCGM FIT BUT)
Deoras Anoop (JHU)
Povey Daniel (JHU)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

recurrent neural network, language model, speech recognition, maximum entropy

Abstract

Techniques for effective training of recurrent neural network based language models are described, and new state-of-the-art results on standard speech recognition task are reported.

Annotation

We describe how to effectively train neural network based language models on large data sets. Fast convergence during training and better overall performance is observed when the training data are sorted by their relevance. We introduce hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model. This leads to significant reduction of computational complexity. We achieved around 10% relative reduction of word error rate on English Broadcast News speech recognition task, against large 4-gram model trained on 400M tokens.

Published
2011
Pages
196-201
Proceedings
Proceedings of ASRU 2011
Conference
IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, Hilton Waikoloa Village Resort, Big Island, Hawaii, US
ISBN
978-1-4673-0366-8
Publisher
IEEE Signal Processing Society
Place
Hilton Waikoloa Village, Big Island, Hawaii, US
BibTeX
@INPROCEEDINGS{FITPUB9775,
   author = "Tom\'{a}\v{s} Mikolov and Anoop Deoras and Daniel Povey and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Strategies for Training Large Scale Neural Network Language Models",
   pages = "196--201",
   booktitle = "Proceedings of ASRU 2011",
   year = 2011,
   location = "Hilton Waikoloa Village, Big Island, Hawaii, US",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4673-0366-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9775"
}
Back to top