Subject
Computational syntax
General details of the subject
- Mode
- Face-to-face degree course
- Language
- English
Description and contextualization of the subject
Este curso presentará los principales enfoques para el tratamiento computacional de la sintaxis. Entre otros, gramáticas sin contexto, sintaxis de estado finito y modelos estadísticos. Se presentarán varios formalismos, como las gramáticas independientes del contexto, gramáticas probabilísticas, gramáticas de unificación, y la gramática de restricciones. También presentaremos una descripción general principal de etiquetado morfosintáctico (Part of Speech tagging), reconocimiento parcial (chunking) y análisis sintáctico de constituyentes y de dependencias (parsing).Se dará una descripción general del papel que desempeñan la morfología y la sintaxis en las aplicaciones que utilizan la tecnología del lenguaje.
Teaching staff
Name | Institution | Category | Doctor | Teaching profile | Area | |
---|---|---|---|---|---|---|
GOJENOLA GALLETEBEITIA, KOLDOBIKA | University of the Basque Country | Profesorado Titular De Universidad | Doctor | Bilingual | Computer Languages and Systems | koldo.gojenola@ehu.eus |
ORONOZ ANCHORDOQUI, MAITE | University of the Basque Country | Profesorado Agregado | Doctor | Bilingual | Computer Languages and Systems | maite.oronoz@ehu.eus |
URIZAR ENBEITA, RUBEN | University of the Basque Country | Profesorado Titular De Universidad | Doctor | Bilingual | Teaching of Language and Literature | ruben.urizar@ehu.eus |
MANS , HULDEN | University of Colorado, Boulder | Otros | Doctor |
Competencies
Name | Weight |
---|---|
Ability to handle, enrich and use language resources for the processing of human language. | 20.0 % |
Understanding of the basic strategies for the analysis of language, and capacity of extending these strategies for their use in applications for language processing. | 20.0 % |
Ability to use and adapt the tools (morphological, syntactic and semantic analyzers) available for different languages. | 20.0 % |
Ability to design and develop resources, tools and computer applications for language technologies. | 20.0 % |
Ability to use and adapt the relevant methods for research on language technologies. | 20.0 % |
Study types
Type | Face-to-face hours | Non face-to-face hours | Total hours |
---|---|---|---|
Lecture-based | 15 | 22.5 | 37.5 |
Applied laboratory-based groups | 30 | 45 | 75 |
Training activities
Name | Hours | Percentage of classroom teaching |
---|---|---|
Computer work practice, laboratory, site visits, field trips, external visits | 75.0 | 40 % |
Lectures | 37.5 | 40 % |
Assessment systems
Name | Minimum weighting | Maximum weighting |
---|---|---|
Attendance and participation | 5.0 % | 5.0 % |
Drawing up reports and presentations | 75.0 % | 75.0 % |
Written examination | 20.0 % | 20.0 % |
Learning outcomes of the subject
Know the basic elements of computational syntax: (a) context-free grammars, (b) probabilistic grammars, (c) unification grammars, (d) constituent-based syntax and (e) dependency syntax.Learn to write code and use libraries for the development of parsers in NLP.
Implementation of specific tasks of computational syntactic analysis with autonomy.
Temary
1.Introducción a la Sintaxis Computacional2. Sintaxis de estado finito
2.1. Asignación de categorías sintácticas (POS tagging)
Basada en el conocimiento (Constraint Grammar)
Basada en datos (métodos estadísticos)
2.2. Chunking
3. Expresiones multipalabra (MWE)
4. Gramáticas independientes del contexto
4.1. Modelo básico
4.2. Gramáticas independientes del contexto probabilísticas
4.3. Gramáticas basadas en unificación
5. Sintaxis de dependencias
5.1. Basada en reglas
5.2. Basada en datos
Bibliography
Basic bibliography
Brian Roark and Richard Sproat. 2007. Computational Approaches to Morphology and Syntax. Oxford University PressD. Jurafsky, James H. Martin. Speech and Language Processing (Second Edition), Prentice Hall, Upper Saddle River, N.J. , 2008.
C. Manning, H. Schütze (1999) Foundations of Statistical Natural Language Processing, MIT Press Cambridge, Mass., 1999.
Bemova A., Hajic J., Hladka B. eta Panevova J. (1999). Morphological and Syntactic Tagging of the Prague Dependency Treebank. Journées Atala, Corpus annotés pour la syntaxe. Paris, France.
Bick, E. (2000). The Parsing System "Palavras": Automatic Grammatical Analysis of Portuguese in a Constraint Grammar Framework, Aarhus University Press, Aarhus.
Basic Constrint Grammar Tutorial for CG-3 (Vislcg3) http://beta.visl.sdu.dk/cg3_howto.pdf
Bird S., Ewan Klein, and Edward Loper. Natural Language Processing with Python --- Analyzing Text with the Natural Language Toolkit (2009). O'Reilly Media. http://www.nltk.org/book/
Chomsky, N. (1957). Syntactic structures. The Hague: Mouton.
Karlsson F., Voutilainen A., Heikkilä J. eta Anttila A. (1995). Constraint Grammar: A Language-independent System for Parsing Unrestricted Text. Mouton de Gruyter, Berlin.
R Socher, J Bauer, CD Manning. Parsing with compositional vector grammars Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics 2013
In-depth bibliography
• Chomsky, N. (1957). Syntactic structures. The Hague: Mouton.
• R Socher, J Bauer, CD Manning. Parsing with compositional vector grammars Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics 2013
• Association for Computational Linguistics (ACL) Anthology: