楼主: Lisrelchen
1449 0

[LECTURE NOTES]EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING [推广有奖]

  • 0关注
  • 62粉丝

VIP

已卖:4194份资源

院士

67%

还不是VIP/贵宾

-

TA的文库  其他...

Bayesian NewOccidental

Spatial Data Analysis

东西方数据挖掘

威望
0
论坛币
50288 个
通用积分
83.6906
学术水平
253 点
热心指数
300 点
信用等级
208 点
经验
41518 点
帖子
3256
精华
14
在线时间
766 小时
注册时间
2006-5-4
最后登录
2022-11-6

楼主
Lisrelchen 发表于 2014-10-15 23:18:29 |AI写论文

+2 论坛币
k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群
赵安豆老师微信:zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

感谢您参与论坛问题回答

经管之家送您两个论坛币!

+2 论坛币

EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING




This course is an introduction to data-driven methods applied to natural language processing. The emphasis is on methods, but we will survey applications such as syntactic parsing, text classification, information extraction, tagging, summarization. The final lectures will deal with statistical machine translation.

Lecturer: Philipp Koehn

TA: Tommy Herbert

Lectures: Monday and Thursday, 5:10pm, changed to: WRB room G.11

Tutorials: Tuesday and Friday, 1pm, AT 4.12
Tutorial group assignments.

TUTORIALS
  • Tutorial 1 was discussed on January 22 (Tuesday) and 25 (Friday).
  • Tutorial 2 will be discussed on February 1 (Friday) and 5 (Tuesday).
  • Tutorial 3 will be discussed on February 8 (Friday) and 12 (Tuesday).
  • The project baseline systems will be presented on February 22 (Friday) and 26 (Tuesday).
  • Tutorial 4 will be discussed on March 4 (Tuesday) and 7 (Friday).
  • Tutorial 5 will be discussed on March 11 (Tuesday) and 14 (Friday).
ASSESSMENT

A single assessment (worth 30%) of the course will be given out late January. You will have to turn in your paper and code at the end of March in class. If you have a problem accessing the data from the web site, it is also available at /home/miles/projects/ner/data-eng/ (English) and/home/miles/projects/ner/data-deu/ (German).

The rest of the marks (70%) will go on the exam. Past exam, solutions.

SYLLABUSExact dates will change and may move around. Topics may shift and change during flight.
NoDateTopicSlidesReference
17 JanIntroduction (I): Words and probabilitydisplay | printMS chapter 1
K chapter 3
210 JanIntroduction (II): Estimation and information theorydisplay | printMS chapter 2
K chapter 3
314 JanLanguage modeling (I): From counts to smoothingdisplay | printMS chapter 6
JM chapter 6
K chapter 7
417 JanLanguage modeling (II): Smoothing and back-offdisplay | printMS chapter 6
JM chapter 6
K chapter 7
521 JanTagging (I): Part-of-speech tagging with HMMdisplay | printMS chapter 9/10
JM chapter 8
625 JanTagging (II): Transformation-Based Learningdisplay | printMS chapter 10
728 JanTagging (III): Maximum Entropy Modelsdisplay | printRatnaparkhi [1996]
Berger et al. [1993]
831 JanParsing (I): Context-free grammars and chart parsingdisplay | printJM chapter 9/12
94 FebProjectdisplay | print-
107 FebParsing (II): Lexicalised and probabilistic parsingdisplay | printJM chapter 12
1111 FebWord sense disambiguationdisplay | printJM section 17.2,
MS chapter 7
Yarowsky [1995]
1214 FebText categorization and clusteringdisplay | printMS chapter 14/16
1318 FebSemantics and discoursedisplay | printCarlson et al. [2001]
Pang and Lee [2005]
1421 FebMachine translation (I): Introductiondisplay | print-
1525 FebMachine translation (II): Word-based models and the EM algorithmdisplay | printK chapter 4
Brown et al. [2003]
-28 FebNO CLASS
163 MarMachine translation (III): Decodingdisplay | printK chapter 6
Koehn [2004]
176 MarMachine translation (IV): Phrase-based modelsdisplay | printK chapter 5
Koehn et al. [2003]
Och and Ney [2002]
1810 MarMachine translation (V): Syntax-based modelsdisplay | printK chapter 11
Yamada and Knight [2002]
Chiang [2005]
Collins et al. [2005]
1913 MarMachine translation (VI): Advanced topicsdisplay | print-
2017 MarReview--

MS refers to "Manning and Schütze", JM refers to "Jurafsky and Martin", K to "Koehn", the three textbooks listed below.

REFERENCESWhen possible, online papers will be made available. As for books, the key references are:

二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

关键词:Processing Empirical processI Language Natural emphasis machine methods natural tagging

您需要登录后才可以回帖 登录 | 我要注册

本版微信群
加好友,备注jltj
拉您入交流群
GMT+8, 2026-1-28 09:34