Statistical Language Models Based on Neural Networks
Statistical Language Models Based on Neural Networks
复制标题
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Vysoké Učení;Technické V Brně;Grafiky A Multimédií;Disertační Práce
中科院分区：
文献类型：
--
作者：
Vysoké Učení;Technické V Brně;Grafiky A Multimédií;Disertační Práce
统计语言模型是许多成功应用的关键部分，例如自动语音识别和统计机器翻译（例如众所周知的Google翻译）。用于估计这些模型的传统技术是基于N gram计数。尽管N-gram的已知弱点和许多领域（语音识别，机器翻译，神经科学，人工智能，自然语言处理，数据压缩，心理学等）的研究社区的巨大努力，N-gram基本上保持了最先进的水平。本文的目标是提出各种基于人工神经网络的语言模型的体系结构。虽然这些模型在计算上比N-gram模型更昂贵，但是利用所提出的技术，可以有效地将它们应用于最先进的系统。与现有的N-gram模型相比，语音识别系统的误词率降低了20%。所提出的基于递归神经网络的模型在著名的Penn Treebank设置上实现了最佳的公开性能。Kazıčová slova jazykován model，neuronová jazykován '，rekurentkován，maximálavientropie，rozpoznávávávávánkoveči，komprese dat，umberlá intelligence
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 N gram 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. Kĺıčová slova jazykový model, neuronová śıt’, rekurentńı, maximálńı entropie, rozpoznáváńı řeči, komprese dat, umělá inteligence