Machine Learning for NLP

Credits: 7,5 hp
Syllabus: 5LN708
Teacher: Joakim Nivre

News

Reading list completed (two articles added for lecture 4). /Joakim (2011-11-15)
If you are a student taking this course, please send an email to joakim.nivre@lingfil.uu.se before the course starts, so that I know how to reach you. Unfortunately, I cannot get your email address through the admission system. /Joakim (2011-11-01)

Schedule

	Date	Time	Room	Content	Reading
1	8/11	13-15	9-2029	Basic concepts of machine learning (Slides, Recording1, Recording2)	Alpaydin 1-2, 19
2	15/11	13-15	9-2029	Decision trees and nearest neighbor (Slides, Recording1, Recording2)	Alpaydin 3, 8.4, 9 Daumé 1-2
3	22/11	13-15	9-2029	Linear classifiers (Slides, Recording1, Recording2)	Alpaydin 10, 11.1-11.4, 13.1-13.3 Daumé 3, 6
4	29/11	13-15	9-2029	Structured prediction (Slides, Recording1, Recording2)	Collins Wallach
5	6/12	13-15	9-2029	Ensemble methods (Slides, Recording1, Recording2)	Alpaydin 17 Daumé 11
6	13/12	13-15	9-2029	Unsupervised learning (Slides, Recording1, Recording2)	Alpaydin 7

All lectures will be broadcast through SUNET's Adobe Connect server. Connect through:

https://connect.sunet.se/ml/

Flash Player 8.0.0.0 or above is required and you will be prompted to allow an add‐in to be installed.

Intended Learning Outcomes

In order to pass the course, a student must be able to

apply basic principles of machine learning to natural language data,
use standard software packages for machine learning,
implement linear models for simple and structured classification,
apply clustering techniques to natural language data,

with a certain degree of independent creativity, clearly stating and critically discussing methodological assumptions, applying state-of-the-art methods for evaluation, and presenting the result in a professionally adequate manner.

Examination and Grading Criteria

The course is examined by means of three assignments:

In order to pass the course, a student must pass each of one of these. In order to pass the course with distinction (Väl godkänt), a student must pass at least two assignments with distinction.

Reading List

Ethem Alpaydin. 2010. Introduction to Machine Learning. Second Edition. MIT Press.
Michael Collins. 2002. Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, 1--8.
Hal Daumé III. 2011. A Course in Machine Learning. Draft.
Hanna M. Wallach. 2004. Conditional Random Fields: An Introduction. Technical Report MS-CIS-04-21. Department of Computer and Information Science, University of Pennsylvania.

Course Evaluation

Course evaluation questionnaire