Computational Linguistics

lingi2263  2020-2021  Louvain-la-Neuve

Computational Linguistics
Due to the COVID-19 crisis, the information below is subject to change, in particular that concerning the teaching mode (presential, distance or in a comodal or hybrid format).
5 credits
30.0 h + 15.0 h
Q1
Teacher(s)
Dupont Pierre; Dupont Pierre (compensates Fairon Cédrick); Fairon Cédrick;
Language
English
Main themes
  • Basics in phonology, morphology, syntax and semantics
  • Linguistic resources
  • Part-of-speech tagging
  • Statistical language modeling (N-grams and Hidden Markov Models)
  • Robust parsing techniques, probabilistic context-free grammars
  • Linguistics engineering applications such as spell or syntax checking software, POS tagging, document indexing and retrieval, text categorization
Aims

At the end of this learning unit, the student is able to :

1 Given the learning outcomes of the "Master in Computer Science and Engineering" program, this course contributes to the development, acquisition and evaluation of the following learning outcomes:
  • INFO1.1-3
  • INFO2.3-4
  • INFO5.3-5
  • INFO6.1, INFO6.4
Given the learning outcomes of the "Master [120] in Computer Science" program, this course contributes to the development, acquisition and evaluation of the following learning outcomes:
  • SINF1.M4
  • SINF2.3-4
  • SINF5.3-5
  • SINF6.1, SINF6.4
Students completing successfully this course should be able to
  • describe the fundamental concepts of natural language modeling
  • master the methodology of using linguistic resources (corpora, dictionaries, semantic networks, etc) and make an argued choice between various linguistic resources
  • apply in a relevant way statistical language modeling techniques
  • develop linguistic engineering applications
Students will have developed skills and operational methodology. In particular, they have developed their ability to

  • integrate a multidisciplinary approach to the edge between computer science and linguistics, using wisely the terminology and tools of one or the other discipline,
  • manage the time available to complete mini-projects,
  • manipulate and exploit large amounts of data.
 
Content
  • Various levels of linguistic analysis
  • (Automated) corpus processing: formating, tokenization, data tagging
  • Probabilistic language models: N-grams, HMMs
  • Part-of-Speech Tagging
  • (Probabilistic) Context-Free Grammars: parameter estimation and parsing algorithms
  • Introduction to Machine Translation
  • Introduction to Deep Learning
  • Typical linguistic applications such as automated completion, POS taggers, parsing or machine translation.
Teaching methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

  • Lectures
  • Practical projects implemented in Python.
By default, lectures can be followed face to face in the auditorium announced in the official schedule. Depending on the number of registered students and the evolution of the sanitary situation, students will be able to follow the lectures as well remotely on Teams.
Practical projects are submitted on line and evaluated on the Inginious platform.
Evaluation methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

The projects are worth 30 % of the final grade, 70 % for the final exam (closed-book).
The projects cannot be implemented again in second session.
The project grades are fixed at the end of the semester and included as such in the global score for the second session.
The final exam is, by default, a written exam (on paper or, when appropriate, on a computer).
These evaluation rules are subject to possible updates due to the sanitary situation. In particular, the relative weights between the projects and the final exam could be adapted.  Such possible updates would be notified to the students by a general announcement  posted on the Moodle site of this course.
Bibliography
Teaching materials
  • Les supports obligatoires sont constitués de l'ensemble des documents (transparents des cours magistraux, énoncés des travaux pratiques, compléments, ...) disponibles depuis le site Moodle du cours.
  • Required teaching material include all documents (lecture slides, project assignments, complements, ...) available from the Moodle website for this course.
Faculty or entity
Force majeure
Teaching methods
Lectures are given online and can be followed remotely. Computing projects are submitted online on the Inginious platform.
Evaluation methods
The final exam is an open book exam to be made individually online
The material for this final exam is the same as in the normal situation (see "supports de cours").
The global grade for the course is based on the projects implemented during the semester (50 %) + on the individual final exam (50 %).
The projects cannot be re-implemented for the second session. Hence, the project grade is fixed at the end of the semester.


Programmes / formations proposant cette unité d'enseignement (UE)

Title of the programme
Sigle
Credits
Prerequisites
Aims
Master [120] in Data Science : Statistic

Master [120] in Linguistics

Master [120] in Computer Science and Engineering

Master [120] in Computer Science

Master [120] in Data Science Engineering

Master [120] in Data Science: Information Technology