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
Teachers: Christian Hardmeier, Yan Shao, Joakim Nivre

News

Schedule

Date Time Room Content Reading
1
27/3
14-16
Chomsky
Introduction to machine learning (YS, CH, JN)
2
3/4
14-16
Chomsky
Decision Trees and Nearest Neighbours. Assignment 1 (CH).
CiML, Ch. 1-2
3
5/4
14-16
Chomsky
Linear Classifiers 1. (CH)
CiML, Ch. 3-4
4
10/4
14-16
2-1024
Linear Classifiers 2. (CH)
CiML, Ch. 5 and 7
5
17/4
14-16
Chomsky
Linear Classifiers from Scratch. Assignment 2. (CH)
.
6
19/4
14-16
16-0042
Linear Classifiers 3. (CH)
CiML, Ch. 9
7
26/4
14-16
2-0024
Generalized linear classifiers. (JN)
CiML, Ch. 6.2, 17.1-17.3
8
3/5
14-16
2-0024
Introduction to Numpy and TensorFlow. (YS)

9
8/5
14-16
Chomsky
Linear Classifiers with TensorFlow. Assignment 3. (YS)

10
15/5
14-16
16-2044
Neural Networks 1. (YS)
CiML, Ch. 10, Olah1
11
17/5
14-16
2-0024
Neural Networks 2. (YS)
Olah2
12
22/5
14-16
Chomsky
Recurrent Neural Networks. Assignment 4. (YS)

13
29/5
14-16
16-0041
Machine learning in NLP. (JN)

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.

Examination and Grading Criteria

The course is examined by means of four assignments:
  1. Decision trees and nearest neighbor classification. Deadline: April 13.
  2. Logistic Regression from Scratch. Deadline: April 27.
  3. Logistic Regression with TensorFlow. Deadline: May 18.
  4. Recurrent Neural networks. Deadline: June 1.

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