Institute of Formal and Applied Linguistics
Charles University, Czech Republic
Faculty of Mathematics and Physics
Unsupervised Machine Learning in NLP
The seminar focuses on deeper understanding of selected unsupervised machine learning methods for students who already have basic knowledge of machine learning and probability models. The first half of the semester is devoted to methods of unsupervised learning using Bayesian inference (Dirichlet-Categorical models, Mixture of Categoricals, Mixture of Gaussians, Expectation Maximization, Gibbs sampling) and implementation of these methods on selected tasks. Other lectures will be devoted to clustering methods, componet analysis and unsupervised inspecting deep neural networks.
About
SIS code: NPFL097
Semester: winter
E-credits: 3
Examination: 1/1 C
Guarantor: David Mareček
Timespace Coordinates
The course will be taught online over Zoom, given the current pandemic. All lectures will be recorded so you can catch up later.
- The lectures in Czech are given on Mondays 10:40 - 12:10, the first lecture is on Oct 5.
- The lectures in English are given on Fridays 10:40 - 12:10, the first lecture is on Oct 9.
All enrolled students will get a Zoom link via email. If you want to take part and have not officialy enrolled, email me.
Course prerequisities
Students are expected to be familiar with basic probabilistic concepts, roughly in the extent of:
- NPFL067 - Statistical methods in NLP I
In the second half of the course, it will be an advantage for you if you know the basics of deep-learning methods. I recommend to attend
- NPFL114 - Deep Learning
Course passing requirements
- There are three programming assignments during the term. For each one, you can obtain 10 points. When submitted after the deadline, you can obtain at most half of the points.
- You can obtain 10 points for an individual 30-minutes presentation about selected machine learning method or task or about a novel approach in the field.
- You pass the course if you obtain at least 20 points.
Lectures
1. Introduction Slides Warm-Up test
2. Beta-Bernoulli probabilistic model Beta-Bernoulli Beta distribution
3. Dirichlet-Categorical probabilistic model, Modeling document collections Dirichlet-Categorical Document collections Categorical Mixture Models Expectation-Maximization
4. Bayesian Mixture Models, Gibbs Sampling, Latent Dirichlet Allocation Gibbs Sampling Gibbs Sampling for Bayesian mixture Latent Dirichlet allocation Algorithms for LDA and Mixture of Categoricals Gibbs Sampling
5. Programming session: Latent Dirichlet Allocation Latent Dirichlet Allocation
6. Chinese Restaurant Process Chinese Restaurant Process Bayessian inference with Tears
7. Programming session: Text Segmentation Chinese Segmentation
8. Unsupervised POS tagging, Word-Alignment, and Dependency Parsing Tagging, Alignment, Parsing
9. Mixture of Gaussians and other clustering methods K-Means and Gaussian Mixture Models Clustering Methods
10. Dimesionality Reduction Dimensionality Reduction
11. Programming session: Clustering and Component Analysis Clustering and Component Analysis on Word Vectors
12. Interpretation of Neural Networks Interpretation of Neural Networks Hidden in the Layers
1. Introduction
Oct 05 Oct 09 (in English)
- Course overview Slides
- revision of the basics of probability and machine learning theory Warm-Up test
2. Beta-Bernoulli probabilistic model
Oct 19 Oct 16 (in English)
- slides for Beta-Bernoulli models by Carl Edward Rasmussen from University of Cambridge
- How to compute expected value of the Beta distribution can be found here: Beta distribution
- Web application showing the Beta-Bernouli distribution from the Coin Experiment is here: Beta Coin Experiment.
- Beta distribution online demo: https://demonstrations.wolfram.com/BetaDistribution/.
3. Dirichlet-Categorical probabilistic model, Modeling document collections
Oct 26 Oct 30 (in English)
- slides for Dirichlet-Categorical and Document collections and Categorical Mixture Models by Carl Edward Rasmussen from University of Cambridge Expectation-Maximization
4. Bayesian Mixture Models, Gibbs Sampling, Latent Dirichlet Allocation
Nov 02 Nov 06 (in English)
- slides for Gibbs Sampling and Gibbs Sampling for Bayesian mixture and Latent Dirichlet allocation by Carl Edward Rasmussen from University of Cambridge
- slides for Algorithms for LDA and Mixture of Categoricals
- see also Chapter 11 in the Bishop's book: Pattern Recognition and Machine Learning
- Gibbs sampling from the bivariate normal distribution: Gibbs Sampling
5. Programming session: Latent Dirichlet Allocation
Nov 09 Nov 13 (in English)
- Assignment 1: Latent Dirichlet Allocation
6. Chinese Restaurant Process
Nov 16 ###e Date: Nov 20 (in English)
- Slides for Chinese Restaurant Process and Unsupervised segmentation of texts Chinese Restaurant Process
- tutorial Bayessian inference with Tears by Kevin Knight (2009)
7. Programming session: Text Segmentation
Nov 23 Nov 27 (in English)
- Assignment 2: Chinese Segmentation
8. Unsupervised POS tagging, Word-Alignment, and Dependency Parsing
Nov 30 Dec 04 (in English)
- Slides: Tagging, Alignment, Parsing
9. Mixture of Gaussians and other clustering methods
Dec 07 Dec 11 (in English)
- Slides K-Means and Gaussian Mixture Models by David Rosenberg from University of New York
- Slides Clustering Methods
10. Dimesionality Reduction
Dec 14 Dec 18 (in English)
- Principal Component Analysis, Independent Component Analysis, Canonical Correlation Analysis
- Slides Dimensionality Reduction
11. Programming session: Clustering and Component Analysis
Dec 21 Dec 18 (in English)
- Assignment 3: Clustering and Component Analysis on Word Vectors
12. Interpretation of Neural Networks
Jan 04 Jan 08 (in English)
- Analysing word embeddings, contextual embeddings, and self-attentions in the NLP neural networks.
- Slides Interpretation of Neural Networks Hidden in the Layers
Latent Dirichlet Allocation
Deadline: Nov 30 23:59 Deadline: Dec 04 23:59 (for English students) 10 points
- Instructions: assignment1.pdf
- Preprocessing procedures: lda-data.py
Chinese Segmentation
Deadline: Dec 14 23:59 Deadline: Dec 18 23:59 (for English students) 10 points
- Instructions: assignment2.pdf
- Input data: data_small.txt
- Evaluation script eval.pl
- Evaluation data: data_small_gold.txt
Clustering and Component Analysis on Word Vectors
Deadline: Jan 18 23:59 Deadline: Jan 15 23:59 (for English students) 10 points
- Instructions: assignment3.pdf
- Input data: nmt-en-dec-512.txt
-
Christopher Bishop: Pattern Recognition and Machine Learning, Springer-Verlag New York, 2006 (read here)
-
Kevin P. Murphy: Machine Learning: A Probabilistic Perspective, The MIT Press, Cambridge, Massachusetts, 2012 (read here)
-
David Mareček, Jindřich Libovický, Tomáš Musil, Rudolf Rosa, Tomasz Limisiewicz: HIDDEN IN THE LAYERS: Interpretation of Neural Networks for Natural Language Processing. Institute of Formal and Applied Linguistics, 2020 (read_here)
