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


Schedule
Learning Outcomes
Examination
Reading List
Course Evaluations


Machine Learning for NLP

Credits: 7,5 hp
Syllabus: 5LN708, 5LN716
Teachers: Joakim Nivre, Yan Shao

News

Schedule

Date Time Room Content Reading
1
7/11
10-12
Turing
Introduction to machine learning.

2
9/11
10-12
Turing
Decision trees and nearest neighbors. Assignment 1.
CiML, Ch. 1-2 (skip 2.4-2.5)
3
16/11
10-12
Turing
Perceptron learning. Assignment 2.
CiML, Ch. 3-4
4
23/11
10-12
Turing
Linear models.
CiML, Ch. 6
5
30/11
10-12
Turing
Probabilistic modeling. Assignment 3.
CiML, Ch. 7
6
7/12
9-11
Turing
Neural networks.
CiML, Ch. 8
7
14/12
10-12
Turing
More on neural networks. Assignment 4.

Intended Learning Outcomes

In order to pass the course, a student must be able to
  1. apply basic principles of machine learning to natural language data,
  2. apply probability theory and principles of statistical inference to natural language data
  3. use standard software packages for machine learning,
  4. implement linear models for classification,
  5. design simple neural networks for natural language data using some standard library
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.

NB: Outcome 5 is only included in the 7.5 credit version of the course.

Examination and Grading Criteria

The course is examined by means of four assignments:
  1. Decision trees and nearest neighbor classification. Deadline: November 16.
  2. Perceptron learning. Deadline: November 30.
  3. Naive bayes classification. Deadline: December 14.
  4. Neural networks. Deadline: January 13.
NB: Assignment 4 is only included in the 7.5 credit version of the course.

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

Reading List