XClose

UCL Module Catalogue

Home
Menu

Statistical Natural Language Processing (COMP0087)

Key information

Faculty
Faculty of Engineering Sciences
Teaching department
Computer Science
Credit value
15
Restrictions
This module is restricted to students registered on: MSc Computational Statistics and Machine Learning MSc Data Science and Machine Learning MSc Machine Learning MSc Data Science (International) MSc Data Science MEng Computer Science MEng Mathematical Computation

Alternative credit options

There are no alternative credit options available for this module.

Description

Aims:
The module introduces the basics of statistical natural language processing (NLP) and machine learning techniques relevant for NLP.

Learning outcomes:
On successful completion of the module, a student will be able to understand relevant ML techniques, in particular in deep learning, what makes NLP challenging (and exciting), how to write programs that process language, and how to address the computational challenges involved.

Content:
NLP is domain-centred fields, as opposed to technique centred fields such as ML, and as such there is no "theory of NLP" which can be taught in a cumulative technique-centred way. Instead this course will focus on one or two NLP end-to-end pipelines (such as Machine Translation and Machine Reading). Through these applications the participants will learn about language itself, relevant linguistic concepts, and Machine Learning techniques. For the latter an emphasis will be on deep learning prediction.

Topics will include (but are not restricted to) machine translation, sequence tagging, constituent and dependency parsing, information extraction, semantics. The course has a strong applied character, with coursework to be programmed and lectures that mix practical aspects with theory and background.

NLP Tasks:

  • Language Models;
  • Machine Translation;
  • Text Classification;
  • Sequence Tagging;
  • Constituency Parsing;
  • Dependency Parsing;
  • Information Extraction;
  • Machine Comprehension.

NLP and ML methods:

  • Encoder/Decoder Architectures;
  • Feature Engineering;
  • Deep Neural Networks;
  • RNNs, CNNs;
  • Attention;
  • Word Vectors;
  • Pretraining.

Requisites:
To be eligible to select this module, a student must ​be registered on a programme for which it is a formally-approved option or elective choice AND must have (i) an understanding of Basic Probability Theory (e.g. Bayes Rule), Linear Algebra and Multivariate Calculus; (ii) proficiency in coding in Python; and (iii) the ability to install libraries on a computer.

Module deliveries for 2020/21 academic year

Intended teaching term: Term 2     Postgraduate (FHEQ Level 7)

Teaching and assessment

Mode of study
Face-to-face
Methods of assessment
30% Coursework 1
40% Coursework 2
30% Coursework 3
Mark scheme
Numeric Marks

Other information

Number of students on module in previous year
132
Module leader
Professor Sebastian Riedel
Who to contact for more information
cs.compgmlds@ucl.ac.uk

Intended teaching term: Term 2     Undergraduate (FHEQ Level 7)

Teaching and assessment

Mode of study
Face-to-face
Methods of assessment
30% Coursework 1
40% Coursework 2
30% Coursework 3
Mark scheme
Numeric Marks

Other information

Number of students on module in previous year
42
Module leader
Professor Sebastian Riedel
Who to contact for more information
cs.compgmlds@ucl.ac.uk

Last updated

This module description was last updated on 5th March 2020.