首页> 美国政府科技报告 >Fast Variational Approach for Learning Markov Random Field Language Models.

【24h】

Fast Variational Approach for Learning Markov Random Field Language Models.

机译：学习马尔可夫随机场语言模型的快速变分方法。

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Language modelling is a fundamental building block of natural language processing. However in practice the size of the vocabulary limits the distributions applicable for this task: specifically one has to either resort to local optimization methods, such as those used in neural language models, or work with heavily constrained distributions. In this work, we take a step towards overcoming these difficulties. We present a method for global-likelihood optimization of a Markov random field language model exploiting long-range contexts in time independent of the corpus size. We take a variational approach to optimizing the likelihood and exploit underlying symmetries to greatly simplify learning. We demonstrate the efficiency of this method both for language modelling and for part-of-speech tagging.

著录项

作者
Jernite, Y.; Rush, A. M.; Sontag, D.;
展开▼
作者单位

展开▼
年度 2015
页码 1-13
总页数 13
原文格式 PDF
正文语种 eng
中图分类工业技术;
关键词
Computational linguistics; Learning machines; Efficiency; Information processing; Markov processes; Maximum likelihood estimation; Natural language; Neural nets; Nonlinear systems; Optimization; Pattern recognition; Semantics; Statistical inference; Stochastic processes; Target classification; Vector analysis; Vocabulary; Part-of-speech tagging; Neural language models; Contextual language models; Markov random field language models;

机译：计算语言学;学习机器;效率;信息处理;马尔可夫过程;最大似然估计;自然语言;神经网络;非线性系统;优化;模式识别;语义学;统计推断;随机过程;目标分类;矢量分析;词汇;部分 - 语音标记;神经语言模型;语境语言模型;马尔可夫随机场语言模型;

相似文献

外文文献
中文文献
专利

1. Learning environmental fields with micro underwater vehicles: a path integral—Gaussian Markov random field approach [J] . Edwin Kreuzer, Eugen Solowjow Autonomous robots . 2018,第4期

机译：使用微水下车辆学习环境领域：路径积分 - 高斯马尔可夫随机现场方法
2. Fast segmentation approach for SAR image based on simple Markov random field [J] . Lei Xiaogang, Li Ying, Zhao Na, Systems Engineering and Electronics, Journal of . 2010,第1期

机译：基于简单马尔可夫随机场的SAR图像快速分割方法
3. Fast segmentation approach for SAR image based on simple Markov random field [J] . Xiaogang Lei, Ying Li, Na Zhao, 系统工程与电子技术：英文版 . 2010,第001期

机译：基于简单马尔可夫随机场的SAR图像快速分割方法
4. A Fast Variational Approach for Learning Markov Random Field Language Models [C] . Yacine Jernite, Alexander M. Rush, David Sontag International Conference on Machine Learning . 2016

机译：学习马尔可夫随机现场语言模型的快速变化方法
5. Covering trees: New variational bounds for map estimation in Markov random fields. [D] . Yarkony, Julian. 2010

机译：覆盖树木：马尔可夫随机场中地图估计的新变分界线。
6. Learning Heterogeneous Hidden Markov Random Fields [O] . Jie Liu, Chunming Zhang, Elizabeth Burnside, -1

机译：学习异构隐马尔可夫随机场
7. FAST-PVE: Extremely Fast Markov Random Field Based Brain MRI Tissue Classification [O] . Jussi Tohka 2013

机译：FasT-pVE：基于极快马尔可夫随机场的脑mRI组织分类

Fast Variational Approach for Learning Markov Random Field Language Models.

摘要

著录项

相似文献

相关主题

期刊订阅