Teaching plan for the course unit

(Short version)

 

Catalą Castellano English Close imatge de maquetació

 

Print

 

General information

 

Course unit name: Computational Linguistics

Course unit code: 361749

Academic year: 2024-2025

Coordinator: Itziar Aduriz Agirre

Department: Department of Catalan Philology and General Linguistics

Credits: 6

Single program: S

 

 

Estimated learning time

Total number of hours 150

 

Face-to-face and/or online activities

46

 

-  Lecture with practical component

Face-to-face

 

46

Supervised project

50

Independent learning

54

 

 

Learning objectives

 

Referring to knowledge

— Analyse the morphological, syntactic, lexical and semantic problems presented by natural language processing (NLP).

— Know the different applications of computational linguistics.

— See how linguistic information is structured in the different modules of these applications.

— Be familiar with the most common techniques and methods of morphological, syntactic and semantic analyses.

 

Referring to abilities, skills

— Acquire skills in the use of computer tools and resources for automatic language analysis and linguistic formalization, critical elements for making any theoretical proposals and for descriptive and/or computational analyses.

 

 

Teaching blocks

 

1. What do we mean by natural language processing (NLP)? What are its goals?

1.1. Research areas

1.2. Standard modules in NLP systems

1.3. Linguistic resources

1.4. The ambiguity of language: the great challenge of NLP

2. Techniques, methods and resources of automatic language analysis

2.1. Empirical methods and knowledge-based methods

2.2. Techniques, processes and resources of morphological analysis

2.3. Techniques, processes and resources of syntactic analysis

2.4. Techniques, processes and resources of semantic analysis

3. NLP applications

3.1. Automatic translation

3.2. Information extraction: document classification and automatic summarization

3.3. Information retrieval and question answering

3.4. Sentiment analysis and opinion mining

3.5. Speech technologies

 

 

Official assessment of learning outcomes

 

Continuous assessment

The default assessment method is continuous assessment made up of the following elements:
— A practical exam (30%) to take place at the beginning of December.
— A theoretical exam (50%) to take place on the date scheduled for this purpose in the Faculty’s exam calendar.
— A practical assignment (20%) to be submitted in mid-November.

To pass the course, students must have taken the two exams, completed the assignment and obtained at least 40% on each element.

 

Examination-based assessment

Students wishing to opt out of continuous assessment may request to be evaluated by means of single assessment, provided they do so in accordance with the terms and conditions established for this purpose by the Faculty.

Single assessment consists of a theoretical exam (60%) and a practical exam (40%).


Repeat assessment

In the re-evaluation test, which will take place on the date assigned by the Faculty, students who have opted for continuous assessment will have the opportunity to retake, at the teacher’s discretion, the exams, tests, or other assessment activities that they have not passed in the previous sitting.  

 

 

Reading and study resources

Check availability in Cercabib

Book

Clark, A., Ch. Fox, Sh. Lappin (2013)  The Handbook of Computational Linguistics and Natural Language Processing, Wiley-Blackwell. ISBN 978-1-118-34718-8.  EnllaƧ

Dale, R., Moisl, H., Somers, H. (Eds.) (2000) Handbook of Natural Language Processing, Nova York, Marcel Dekker.  EnllaƧ

Hovy, D. (2020). Text Analysis in Python for Social Scientists: Discovery and Exploration. Cambridge University Press.

https://www.cambridge.org/core/elements/text-analysis-in-python-for-social-scientists/BFAB0A3604C7E29F6198EA2F7941DFF3

Jurafsky D. & Martin, J. (2009) Speech and Language Processing, New Jersey (USA) Pearson Education.  EnllaƧ

Kübler, S., R.McDonald, J. Nivre (2009) Dependency Parsing. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers. ISBN: 978-1598295962.  EnllaƧ

M. A. Martí i M. Taulé (2014) Computational Hispanic Linguistics, a The Routledge Handbook of Hispanic Applied Linguistics, London and New York, Routledge.  EnllaƧ

Martí M. A. (coord.) (2000) Les tecnologies del llenguatge, Edicions de la Universitat Oberta de Catalunya, EDIUOC, pàg. 1- 272: versió en castellà publicada: Martí M. A. (coord.) (2003) Tecnologías del lenguaje, Barcelona, Editorial Universitat Oberta de Catalunya.  EnllaƧ

Martí M. A. i I. Castellón (2001) Lingüística Computacional, pàg.: 1-160. Barcelona, Edicions UB.  EnllaƧ

Martí M. A. y J. Llisterri (editores) (2004) Tecnologías del texto y del habla, Barcelona, Edicions UB. ISBN: 84-475-2647-X.  EnllaƧ

Martí M. A. y J. Llisterri (editores) (2002) Tratamiento del Lenguaje Natural, Barcelona, Edicions UB. ISBN: 84-475-2647-X.  EnllaƧ

Mitkov, R. (Ed.) (2003) The Oxford Handbook of Computational Linguistics, Oxford/Nova York, Oxford University Press.  EnllaƧ

Fonts d’informació complementàries:

Badia, T. (2000) Llengua catalana IV Tècniques de processament del llenguatge, a Martí (ed.) Barcelona, Edicions UOC.  EnllaƧ

Grishman, R. (1994), Computational Linguistics. An Introduction, Cambridge, Cambridge University Press.  EnllaƧ

Grishman, R. (1991),  Introducción a la lingüística computacional. Madrid, Visor.  EnllaƧ

McEnery and Wilson (1997) Corpus Linguistics, Edinburgh University Press.  EnllaƧ

Miller, G. (1990) "WordNet: An on-line lexical Database", a International Journal of Lexicography, vol 3. Oxford Univ. Press.  EnllaƧ

Rodríguez et. al (2001) Mètodes robustos per a l’anàlisi del llenguatge, a Martí (ed.) Lingüística Computacional. Barcelona, Ed. UOC.  EnllaƧ

Electronic text

Bird S., Klein E., Loper , E. (2009), Natural Language Processing: Analyzing Text with Python and the Natural Language Toolkit.  EnllaƧ

SpaCy: Industrial-Strength Natural Language Processing in Python.