UPPSALA UNIVERSITET : Inst. f. lingvistik och filologi : STP
Uppsala universitet

Schedule
Learning Outcomes
Examination
Reading List
Course Evaluation


Machine Learning for Language Technology (Candidate and Master, 2015)

Credits: 7,5 hp
Teachers: Marina Santini, Joakim Nivre.
Contact person: Marina Santini santinim [AT] stp.lingfil.uu.se

Venue: Department of Linguistics and Philology, Uppsala University, Room 9-2043 (Chomsky) [Map].

Syllabus, Candidate Students: 5LN454 (Swedish)
Syllabus, Master Students 5LN708 (English)



News



Schedule and List of Topics

Last Updated: 23 December 2015.

Lect Date Time Room Content Reading
1
10/11
10:15-12:00
9-2043
(Chomsky)
Introduction to the Course
(Pdf, Slideshare)

What is Machine Learning?
(Pdf, Slideshare)
- The Flipped Classroom: David Black-Schaffer's talk
- Daume' (2015): pp. 8-10
- Witten et al. (2011): Ch 1
2
12/11
10:15-12:00
9-2043
(Chomsky)
Preliminaries
(Pdf, Slideshare, Lab)
- Witten et al. (2011): Ch 2; Ch 10;
Ch 11: 407-410; Ch17: 559-562.
3
17/11
10:15-12:00
9-2043
(Chomsky)
Basic Concepts (Induction & Evaluation)
(Pdf, Slideshare)

Decision Trees (I) (Pdf, Slideshare, Lab)
- Daume' III (2015): 10-16; 19-23; 60-62
- Witten et al. (2011): 410-416, 562-565
4
20/11
10:15-12:00
9-2043
(Chomsky)
Decision Trees (II) (Pdf, Slideshare, Lab) - Daume' III (2015): 16-18; 51-58
- Witten et al. (2011): 99-108; 195-203; 487-494;
567; 575-577
5
24/11
10:15-12:00
9-2043
(Chomsky)
Probability Theory (Repetition)

Statistical Inference
(Pdf01, Pdf02, Slideshare02, Lab)
- Witten et al. (2011): 150-152
6
26/11
10:15-12:00
9-2043
(Chomsky)
Statistical Learning (I)
(Pdf, Lab)
- Daume' III (2015): Ch 7: 103-110
7
01/12
10:15-12:00
9-2043
(Chomsky)
Statistical Learning (II) (Pdf, Lab) - Daume' III (2015): Ch 2: 24-26 (Feat.Vectors)
- Daume' III (2015): Ch 7: 111-115 (Logistic Regres.)
8
03/12
10:15-12:00
9-2042
(Turing)
Machine Learning in Practice (I)
Predicting Performance
(Pdf, Slideshare Lab)
- Daume' III (2015): 65-67
- Witten et al. (2011): 156-180; 505-515
9
07/12
10:15-12:00
9-2043
(Chomsky)
Machine Learning in Practice (II)
(Pdf, Slideshare Lab)
A Few Useful Things to Know about ML
- Daume' III (2015): 53-64
- Witten et al. (2011): 147-156
10
10/12
10:15-12:00
9-2043
(Chomsky)
Perceptron (I)
(Pdf, Lab, StarterCode)
- Daume' III (2015): 37-46
11
15/12
10:15-12:00
9-2043
(Chomsky)
Perceptron (II)
Pdf
- Daume' III (2015): 46-50
- Python-based lab

Expected Learning Outcomes

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

* apply basic principles of machine learning to natural language data;

* show theoretical knowledge of the following machine learning methods:
- decision trees
- perceptron
- probabilistic modelling

* use standard machine learning software for practical classification
and result evaluation.

Attendance, Examination and Grading Criteria

Attendance: There is a mandatory 80% attendance requirement for both the lectures delivered through the online platform AND for the in-class lab sessions that will take place at the Department of Linguistics and Philology, Uppsala University, Room 9-2043 (Chomsky) [Venue].
If a student fails to fulfill this requirement, additional assignments will have to be completed prior to passing the course. The choice of the topic will relate to the missed material.

Examination and Grading Criteria:The course is examined by means of 7-9 lab assignments started in class and completed at home.
The following marks will be used: In order to receive the passing grade on the course (G), a student must get at least five Gs out of all the submitted lab assignments. In order to receive pass with distinction (VG), the majority of all the submitted lab assignments have to meet the criteria for distinction.

The course also includes:Quizzes: The completion of quizzes is mondatory. Quizzes are not graded.

A student is also entitled to repeat the course, depending on available capacity.

Reference List (Required Reading)



© 2015. UPPSALA UNIVERSITET, Institutionen för lingvistik och filologi
Box 635, 751 26 Uppsala, Sweden. Web page updated by: Marina Santini.