Computational Linguistics - 1st semester
Objectives
Acquisition of knowledge in the field of Computational Linguistics allowing students:
a) to develop basic skills for the analysis and understanding of natural languages and of natural languages functioning aiming at computation;
b) to understand the levels of computer-aided treatment involved in the processing and computation of natural languages;
c) to know the different current strategies and tools for the processing and computation of natural languages;
d) to acquire methodologies for the computer-aided analysis and treatment of linguistic data;
e) to make use, in practical scenarios, of the acquired knowledge.
General characterization
Code
711131021
Credits
6
Responsible teacher
Raquel Fonseca Amaro
Hours
Weekly - 4
Total - Available soon
Teaching language
Portuguese
Prerequisites
None.
Bibliography
Allen, J. (1995) Natural Language Understanding, Menlo Park, CA: Benjamim Cummings.
Baldwin, T. (2005) General-Purpose Lexical Acquisition: Procedures, Questions and Results, in Proc. of the Pacific Association for Computational Linguistics 2005, Tokyo, Japan.
Bolshakov, I. & Gelbukh, A. (2004) Computational Linguistics: Models, Resources, Applications, México: IPN, UNAM, FCE.
Branco, A., Mendes, S. & Ribeiro R. (eds.) (2004) Language Technology for Portuguese: shallow processing tools and resources, Lisboa: Edições Colibri.
Manning & Schütze (1999) Foundations of Statistical Natural Language Processing, MIT Press.
Mitrov, R. (2003) The Oxford Handbook of Computational Linguistics, Oxford: Oxford University Press.
Pustejovsky, J. (1995) The Generative Lexicon, The MIT Press.
Sag & Wasow (1999) Syntactic Theory - A Formal Introduction, Stanford:CSLI Publications.
Teaching method
Theoretical and practical classes and tutorial guidance, with resource to case studies and practical application of the acquired knowledge, including: i) topic presentation and explanation by the teacher; ii) discussion and analytic analysis of relevant literature on the addressed topics; iii) practical application of acquired knowledge in individual and collective essays within specific tasks.
Evaluation method
Continuous evaluation, including the following components: individual and collective essays, with presentation and discussion in class (accounting for 55% of the final grade); and final individual test (accounting for 45% of the final grade).
Subject matter
1. Linguistics, computation and natural language processing
2. Products, tools and areas from Computer Linguistics
2.1 Shallow processing
2.2 Grammar and style checking
2.3 Information retrieval and summarization
2.4 Automatic translation
2.5 Natural language interface
2.6 Natural language recognition and generation
2.7 Language understanding
3. Computational Linguistics historical perspective and theoretical grounding
3.1 Structuralist approach and Chomsky
3.2 Context-free grammars and transformational grammars
3.3 Valencies, interpretation and constraints
3.4 HPSG and unification
3.5 Corpus Linguistics
3.6 Automatic acquisition
4. Practical application to Portuguese
4.1 Regular expressions
4.2 Grammars and parsing
4.3 Feature structures and unification