Natural Language Processing

Natural language processing (NLP) deals with the application of computational models to text or speech data. Application areas within NLP include automatic (machine) translation between languages; dialogue systems, which allow a human to interact with a machine using natural language; and information extraction, where the goal is to transform unstructured text into structured (database) representations that can be searched and browsed in flexible ways. NLP technologies are having a dramatic impact on the way people interact with computers, on the way people interact with each other through the use of language, and on the way people access the vast amount of linguistic data now in electronic form. From a scientific viewpoint, NLP involves fundamental questions of how to structure formal models (for example statistical models) of natural language phenomena, and of how to design algorithms that implement these models.

In this course you will study mathematical and computational models of language, and the application of these models to key problems in natural language processing. The course has a focus on machine learning methods, which are widely used in modern NLP systems: we will cover formalisms such as hidden Markov models, probabilistic context-free grammars, log-linear models, and statistical models for machine translation. The curriculum closely follows a course currently taught by Professor Collins at Columbia University, and previously taught at MIT.

课程大纲

1. Language modeling.
2. Hidden Markov models, and tagging problems.
3. Probabilistic context-free grammars, and the parsing problem.
4. Statistical approaches to machine translation.
5. Log-linear models, and their application to NLP problems.
6. Unsupervised and semi-supervised learning in NLP.

课程评论(7条)

1	妖秀死仔 2013-06-25 10:41 1 票支持; 0 票反对断断续续花了一个月，终于修完这门课了。各种模型和算法讲解的很详细，入门推荐。

1	蒋勇NLP 2013-05-25 19:34 1 票支持; 0 票反对 collins大牛的课程，大赞啊。。从NLP的基础语言模型讲到机器学习的一些算法，每个算法讲解都很细致，并举很好的例子来进行阐述，每个讲义都有note，当时学习时候并没有仔细学，现在正在复习ing。。

1	课程图谱 2013-05-23 14:25 1 票支持; 0 票反对这门课程由哥伦比亚大学教授，大神Michael Collins授课，吴军老师在数学之美中也对他进行了介绍--“柯林斯：追求完美“，还想继续了解他的同学可以Google。

某李的技术博客 2013-05-17 09:59 5 票支持; 0 票反对

非常好的一门课，不像其他课程那么水，完完整整的哥伦比亚课程，如果认真学完肯定收获很多，花的时间绝对物有所值。科林斯的讲解非常清晰，内容涵盖了语言建模，解码算法，学习算法几个方面。

语言及翻译模型：n元模型，HMM模型，log-linear模型，GLM模型，IBM 1模型，IBM2 模型，phrase-based翻译模型，PCFG语法，LPCFG语法

解码算法：Viterbi算法，CKY算法，GLM Viterbi算法

学习算法：Brown聚类算法，Perceptron算法，EM算法

应用举例：词性标注/实体识别(HMM, GLM, log-linear)，语法树标注(PCFG, dependecny-based)，机器翻译

0	呵公要当攻城狮 2013-05-14 16:41 0 票支持; 0 票反对 Proferssor Collins讲课十分清晰，课程大体覆盖到了NLP的比较基础的内容，编程作业十分具有针对性，由于不是特别熟悉python，我做起来特别费劲，基本上每个PA我都做了10小时以上。课程难度中上，建议有一定python和machine learning基础的同学学习。

1	EyonFresh 2013-05-14 10:09 2 票支持; 1 票反对我的第一门MOOC课程，无论是教学还是编程作业，都精彩的没话说。我认为难度属于中上。为了完成相应编程，还在edx上学了一门python语言的课，可惜这个课跟的太晚，没法系统的跟着学习了。

0	ototsuyume 2013-05-13 21:46 1 票支持; 1 票反对跟斯坦福那门nlp比起来，这门的理论性更强，学起来也稍为枯燥一点，但是各种模型讲得很简单明了，推荐看了斯坦福的nlp后再来学这个

课程详情

课程大纲

课程评论(7条)

课程简介

课程标签

418人关注该课程

主题相关的课程