PhD. Theses

Year: Supervisor: 
Student:  Title: 
Keywords: 

STATISTICAL LANGUAGE MODELS BASED ON NEURAL NETWORKS

Dissertation:2012
Student:Mikolov Tomáš, Ing.
Supervisor:Černocký Jan, doc. Dr. Ing.
Department:Department of Computer Graphics and Multimedia FIT BUT
Status:defended
Date:2012-10-02
Files:
Keywords
language model, neural network, recurrent, maximum entropy, speech recognition, data compression, artificial intelligence
Abstract
Statistical language models are crucial part of many successful applications, such as automatic speech recognition and statistical machine translation (for example well-known Google Translate). Traditional techniques for estimating these models are based on Ngram counts. Despite known weaknesses of N-grams and huge efforts of research communities across many fields (speech recognition, machine translation, neuroscience, artificial intelligence, natural language processing, data compression, psychology etc.), N-grams remained basically the state-of-the-art. The goal of this thesis is to present various architectures of language models that are based on artificial neural networks. Although these models are computationally more expensive than N-gram models, with the presented techniques it is possible to apply them to state-of-the-art systems efficiently. Achieved reductions of word error rate of speech recognition systems are up to 20%, against stateof-the-art N-gram model. The presented recurrent neural network based model achieves the best published performance on well-known Penn Treebank setup.
ISO 690 Citation
MIKOLOV, Tomáš. STATISTICAL LANGUAGE MODELS BASED ON NEURAL NETWORKS. Brno, 2012. Available from: http://www.fit.vutbr.cz/study/DP/PD.php?id=283. PhD. Thesis. Brno University of Technology, Faculty of Information Technology. 2012-10-02. Supervisor Černocký Jan.
BibTeX
@PHDTHESIS{
    author = {Tom{\'{a}}{\v{s}} Mikolov},
    title = {STATISTICAL LANGUAGE MODELS BASED ON NEURAL
	NETWORKS},
    school = {Brno University of Technology,
		Faculty of Information Technology},
    year = {2012},
    location = {Brno, CZ},
    url = {http://www.fit.vutbr.cz/study/DP/PD.php?id=283}
}

Your IPv4 address: 54.158.55.5
Switch to IPv6 connection

DNSSEC [dnssec]