寄托天下 寄托天下
查看: 5327|回复: 3

[公开课] [Coursera] Natural Language Processing 自然语言处理 [复制链接]

Rank: 6Rank: 6

声望
304
寄托币
2167
注册时间
2010-11-13
精华
0
帖子
428
发表于 2013-5-24 14:03:00 |显示全部楼层
这门课主要介绍一些自然语言处理的基本方法和概念,授课教授是哥伦比亚大学Michael Collins教授。最近的一期刚刚在coursera上结课,我是从头到尾跟着deadline做了所有的quiz和编程作业,最后取得了103/100的成绩。感觉这门课对于入门NLP还是很有帮助的,在这里向大家推荐一下。

我先发个帖子介绍一下课程内容,随后更新第一周的slides,视频和quiz。

Course Description:

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.

Problem Sets:

There were will be 3 programming assignments during the class, due roughly every two weeks.

Syllabus:

Topics covered include:

Language modeling.
Hidden Markov models, and tagging problems.
Probabilistic context-free grammars, and the parsing problem.
Statistical approaches to machine translation.
Log-linear models, and their application to NLP problems.
Unsupervised and semi-supervised learning in NLP.
Readings:
Notes for the class will be posted at http://www.cs.columbia.edu/~mcollins

具体内容:


Week 1 - Introduction to Natural Language Processing
Week 1 - The Language Modeling Problem
Week 1 - Parameter Estimation in Language Models
Week 2 - Tagging Problems, and Hidden Markov Models
Week 3 - Parsing, and Context-Free Grammars
Week 3 - Probabilistic Context-Free Grammars (PCFGs)
Week 4 - Weaknesses of PCFGs
Week 4 - Lexicalized PCFGs
Week 5 - Introduction to Machine Translation (MT)
Week 5 - The IBM Translation Models
Week 6 - Phrase-based Translation Models
Week 6 - Decoding of Phrase-based Translation Models
Week 7 - Log-linear Models
Week 8 - Log-linear Models for Tagging (MEMMs)
Week 8 - Log-Linear Models for History-based Parsing
Week 9 - Unsupervised Learning: Brown Clustering
Week 9 - Global Linear Models (GLMs)
Week 10 - GLMs for Tagging
Week 10 - GLMs for Dependency Parsing
已有 1 人评分寄托币 声望 收起 理由
Jackit + 10 + 10 赞一个!

总评分: 寄托币 + 10  声望 + 10   查看全部投币

回应

使用道具 举报

Rank: 6Rank: 6

声望
304
寄托币
2167
注册时间
2010-11-13
精华
0
帖子
428
发表于 2013-5-27 12:52:24 |显示全部楼层

使用道具 举报

Rank: 2

声望
40
寄托币
322
注册时间
2010-10-23
精华
0
帖子
30

2015 US-applicant

发表于 2013-6-15 15:00:44 |显示全部楼层
很好  国内比较系统的语音处理教材就那么两三本   看看别人的。

使用道具 举报

Rank: 2

声望
50
寄托币
3
注册时间
2015-9-6
精华
0
帖子
1
发表于 2015-9-6 19:40:51 |显示全部楼层
您好,视频和课件还能提供下载吗

使用道具 举报

RE: [Coursera] Natural Language Processing 自然语言处理 [修改]
您需要登录后才可以回帖 登录 | 立即注册

问答
Offer
投票
面经
最新
精华
转发
转发该帖子
[Coursera] Natural Language Processing 自然语言处理
https://bbs.gter.net/thread-1586624-1-1.html
复制链接
发送
报offer 祈福 爆照
回顶部