Kursöversikt

The purpose of this course is to provide an introduction to probabilistic modeling and statistical machine learning techniques in terms of their use within the field of language technology. We will review foundational concepts in mathematics and apply them to basic techniques and applications in statistical NLP.  We will also learn practical skills in programming text processing pipelines and analytical tools.

The course syllabus in full as adopted by the head of department is available at the following address:

Syllabus LT 2222 (eng)

Kursplan LT2222 (sv)

 

Teachers

Course organizer & lecturer: Sharid Loáiciga (sharid.loaiciga@gu.se), webpage.

Teaching assistants: Maria Szawerna (maria.szawerna@gu.se)

Administrators

Education coordinator: Madelaine Miller (e-mail: madelaine.miller@.gu.se)

Student administration: flov@flov.gu.se

 

Schedule

Course schedule should be available via TimeEdit:

https://cloud.timeedit.net/gu/web/schema/ri1X5015Z9107vQQ5wZ6779Y55yY5Y27QQ.html

However, we do not recommend relying on it, as it lists rooms we are not using, and we do not have direct editing power over it.  Instead, follow the announcements -- the general gist of the schedule is that there will be regular sessions on Tuesdays and Thursdays 13:15-15:00 and help sessions for extant assignments on Wednesdays mornings, and the course will end on 2025-03-25.
The first meeting will be on Tuesday 2025-01-21.
The following sessions will be self-study:
2025-02-13 (week7), 2025-02-18 & 2025-02-20 (week 8)
 

For remote attendance

Remote attendance is possible through Zoom using the following information

 

Meeting ID: 637 1914 2218
Passcode: 472925 

 

https://gu-se.zoom.us/j/63719142218?pwd=bwhrTX2Zg7KUA2OrsyJN0eNZqRC1ZU.1

 

 

Examination policy

There is no written examination for the course (please ignore any scheduling information to the contrary).

The course will instead be examined through a series of 4 assignments that focus on organizing and transforming data for NLP machine learning and statistical modeling. There won't be any graded labs or quizzes, just the assignments.  Each assignment will have equal weight, even if the score denominator is different between assignments.

Extensive bonus points may be offered in the programming assignments and calculated proportionately into the grade. 

A grade of G will be given for a 50% of the whole course.

A grade of VG will be given for 90% of the whole course.

 

Literature V25

  • Daniel Jurafsky and James Martin (2008) An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Third Edition. Online draft.
  • Delip Rao, Brian McMahan (2018) Natural Language Processing with PyTorch: Build Intelligent Language Applications Using Deep Learning. O'Reilly. Available from library and bookstore.

Online guides that will be useful during the course

Note: Canvas Student Guide available at the following Link

 

 

Content Plan*

*NB: Contents and pace will be adjusted as needed

Week Content Comment
Materials Published Due
4 (Jan 20-26)

Introduction, high-level classification, black-box classification

 

Math review

0_admin.pdf

1_intro.pdf

 

2_handout.pdf

2_handout_with_class_notes.pdf

Blog post on information entropy

5 (Jan 27-Feb2) Dimensionality reduction, svd, vector space classification, perceptron, SVMs

Kunilovskaya et al. 2023

3_handout.pdf

Optional: Tutorial on the math behind SVD

 

Example: simple perceptron.py

Assignment 1
6 (Feb 3-9) Logistic regression, learning process overview NO LAB SESSION ON 5.02.2025

J&M chapter 5

4_handout.pdf

5_handout.pdf

basketball_logit_code.ipynb

7 (Feb 10-16) MaxEnt EXTRA LAB SESSION ON 13.02.2025

6_handout.pdf

 

demo_SVMs

Assignment 1
8 (Feb 17-23) Self-study

no lecture session on 2025-02-18

Assignment 2
9 (Feb 24-Mar 2) FFNs

Reading material: J&M ch 7 or NMT ch 5 by Philipp Koehn (also available in the GU library)

NN online demo

xor-example.pdf

Jupyter notebook on Pytorch basics (from Rao and McMahan's book linked above)

7_handout.pdf

 

10 (Mar 3-9) Perplexity, backpropagation, regularization NO LAB SESSION ON 2025-03-05

Reading material: Backpropagation explanation 1 or explanation 2

nns_recipe.pdf

8_handout.pdf

Recommended extra reading: NMT ch 10 by Philipp Koehn

Assignment 3 Assignment 2
11 (Mar 10-16) RNNs, LSTMs, Attention

Video: Stanford lecture introducing RNNs

Stanford slides on RNNs

Stanford slides on LSTMs, MT and attention

 

Recommended extra reading:

Attention? Attention!

The illustrated transformer

12 (Mar 17-23) Transformer

J&M ch9

J&M slides

Optional:

Original transformer paper by Vaswani et al 2017

ML questions

Assignment 4 Assignment 3
13 (Mar 24-30) Final thoughts, ethics in NLP last lecture on 2025-03-25

Practical Methodology

13_slides

 

14 (Mar 31 - Apr 6) Assignment 4