Computational Linguistics

Code:

CL037

Acronym:

LC

Keywords
Classification	Keyword
OFICIAL	Linguistics

Instance: 2024/2025 - 2S

Active?	Yes
E-learning page:	https://moodle.up.pt/
Responsible unit:	Department of Portuguese and Romance Studies
Course/CS Responsible:	Bachelor in Language Sciences

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
CL	7	study plan	2	-	6	41	162

Teaching language

Suitable for English-speaking students
Obs.: Português

Objectives

This curricular unit aims to provide students with basic knowledge in computational linguistics, by encouraging their critical skills and competences to accurately and soundly reflect on computational approaches to language sciences.

Learning outcomes and competences

By the end of the semester, the students should be able to:
- Demonstrate an understanding of the basic concepts of computational linguistics and human language technology;
- Identify existing applications of computational tools to address linguistic issues;
- Plan basic data mining and natural language processing projects;
- Discuss the ethical challenges of computational linguistics;
- Identify and use existing basic natural language processing tools.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

n/a

Program

1. Introduction. Linguistics, Computation and Computational Linguistics: basic concepts.
2. Technology, applications and potential.
3. Human language technologies and computational linguistics.
4. Natural language processing: tools and applications.
5. Information extraction and information retrieval.
6. Corpus linguistics.
7. Language technologies and speech technologies.
8. Ethical computational linguistics.

Mandatory literature

Alexander Clark; The^handbook of computational linguistics and natural language processing. ISBN: 978-1-4051-5581-6
Ruslan Mitkov; The Oxford handbook of computational linguistics. ISBN: 978-0-19-957369-1
Bird, S. & Klein, E.; Computational Linguistics, Cambridge University Press, 2020
Gama, J., Carvalho, A., Faceli, K., Lorena, A. & Oliveira, M.; Extração de Conhecimento de Dados, Silabo, 2012
Hausser, R.; Foundations of Computational Linguistics: Human-Computer Communication in Natural Language, Springer, 2014
Jurafsky, D. & Martin, J. H.; Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice Hall, 2018
Srinivasa-Desikan, B.; Natural Language Processing and Computational Linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras, Packt, 2018

Comments from the literature

Other aditional bibliographical references as well as materials important to the classes are available in Moodle.

Teaching methods and learning activities

The course unit consists of theoretical and pratical sessions, complemented by tutorials. The theoretical and practical sessions include the presentation of theoretical contents, followed by practical exercises aimed at testing the student’s knowledge, while allowing them to identify problems and gain insight into the contents as a whole. The students will be actively encouraged to conduct practical tasks that real and concrete issues in the field of computational linguistics. The student will be faced with problem-solving tasks.

Software

Python

keywords

Humanities > language sciences > Linguistics

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Teste	50,00
Trabalho escrito	50,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Estudo autónomo	121,00
Frequência das aulas	41,00
Total:	162,00

Eligibility for exams

Students are expected to attend 75% of classes, unless otherwise agreed.

Calculation formula of final grade

Distributed evaluation with final exam. 

Written test: 50%
Written assignment: 50%

In order to pass the curricular unit students need to obtain a minimum grande of 9.5 points in each of the assessment components (test and written assignment) and an average of at least 10 points (in a 0-20 point scale).

Distributed evaluation is encouraged, while the exam is left for exceptional. In the case of the latter, the weighing of the exam is 50%.

Examinations or Special Assignments

N/A

Internship work/project

N/A

Special assessment (TE, DA, ...)

Working students and other exceptions laid down in the regulations should contact the teaching staff in the beggning of the semester to set an alternative assessment procedure.

Classification improvement

Students wishing to improve their final grade or repeat their assessment will have to repeat the written test.