Introduction to Computational Linguistics

Here are links to the course home page and the formal TQA description.

Description

The course provides: 1) an introduction to the theory and practice of computational approaches to natural language processing. Topics include formal models of natural language; standard approaches to processing (morphological analysis, part-of-speech tagging, syntactic parsing and chunking) and word sense disambiguation, 2) exposure to techniques and tools used to develop practical, robust systems that can communicate with users, 3) experience in programming with Python, 4) insight into many open research problems in natural language processing, e.g., summarization, machine translation, information extraction, question answering, response generation, and statistical corpus analysis.

Syllabus

• Overview of Computational Linguistics.
• Introduction to scripting for text processing.
• Lexical and morphological structure.
• Using Regular Expressions.
• Tokenization, stemming and part-of-speech tagging.
• Context free grammars, verb subcategorization and parsing.
• Partial parsing and chunking.
• Word sense disambiguation.

Assessed Coursework

Two assignments throughout the course. These will require some programming in Python.

References:

*** D. Jurafsky, J. H. Martin: Speech and Language Processing. Prentice-Hall, 2000.

* M. Lutz, D. Ascher: Learning Python. O'Reilly, 1999.

* C. Manning, H. Schutze: Foundations of Statistical Natural Language Processing. MIT Press, 1999