Data Intensive Linguistics

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: Sebastian Riedel

Lectures: Mondays and Thursdays, 14:00, FH Room A9/11

Tutorials: Tuesday or Wednesday 13:00, AT 5.01
Tutorial group assignments.

Tutorials

Tutorial 1 was discussed on January 24/25
Assessment was discussed on January 31/February 1
Tutorial 2 was discussed on February 7/8
Tutorial 3 was discussed on February 14/15
Initial presentations of the assignment were presented on February 21/22
Tutorial 4 was discussed on February 28/March 1
Tutorial 5 was discussed on March 7/8

Assessment

A single assessment (worth 30%) of the course was given out on January 30. You will have to turn in your paper and code on March 23 in class.

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

Syllabus

No	Date	Topic	Slides	Reference
1	9 Jan	Introduction (I): Words and probability	display \| print	MS chapter 1
2	12 Jan	Introduction (II): Estimation and information theory	display \| print	MS chapter 2
3	16 Jan	Language modeling (I): From counts to smoothing	display \| print	MS chapter 6 JM chapter 6
4	19 Jan	Language modeling (II): Smoothing and back-off	display \| print	MS chapter 6 JM chapter 6
5	23 Jan	Tagging (I): Part-of-speech tagging with HMM	display \| print	MS chapter 9/10 JM chapter 8
6	27 Jan	Tagging (II): Transformation-Based Learning	display \| print	MS chapter 10
7	30 Jan	Project	display	-
8	2 Feb	Tagging (III): Maximum Entropy Models	display \| print	Ratnaparkhi [1996] Berger et al. [1993]
9	6 Feb	Parsing (I): Context-free grammars and chart parsing	display \| print	JM chapter 9/12
10	9 Feb	Parsing (II): Lexicalised and probabilistic parsing	display \| print	JM chapter 12
11	13 Feb	Word sense disambiguation	display \| print	JM section 17.2, MS chapter 7 Yarowsky [1995]
12	16 Feb	Text categorization and clustering	display \| print	MS chapter 14/16
13	20 Feb	Semantics and discourse	display \| print	Carlson et al. [2001] Pang and Lee [2005]
-	23 Feb	NO LECTURE	-	-
14	27 Feb	Machine translation (I): Introduction	display \| print	-
15	2 Mar	Machine translation (II): Word-based models and the EM algorithm	display \| print	Brown et al. [2003]
16	6 Mar	Machine translation (III): Decoding	display \| print	Koehn [2004]
17	9 Mar	Machine translation (IV): Phrase-based models	display \| print	Koehn et al. [2003] Och and Ney [2002]
18	13 Mar	Machine translation (V): Syntax-based models	display \| print	Yamada and Knight [2002] Chiang [2005] Collins et al. [2005]
19	16 Mar	Machine translation (VI): Advanced topics	display part2\| print part2	-
-	20 Mar	NO LECTURE	-	-
20	23 Mar	Review	-	-

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

Topics may shift and change during flight.

References

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

Foundations of Statistical Natural Language Processing. Christopher Manning and Hinrich Schütze. Available online.
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Daniel Jurafsky and James H. Martin

Home : Teaching : Courses