29853 - Computational Linguistics (LM)

Academic Year 2012/2013

Learning outcomes

The course will examine in detail some of the main topics in Natural Language Processing placing particular emphasis on advanced empirical methods used for linguistic analysis.

Course contents

Introduction

  • Natural Language Processing - Problems and perspectives
  • Basic corpus linguistics
  • Fundamentals of probability calculus
  • N-grams and language models


Natural Language Processing

  • Machine learning techniques.
  • Methods for evaluating application performances in Computational Linguistics.
  • Linguistics from a computational point of view.
    • Computational phonetics
      • Audio sample properties - phones and formants
        Frequency Analysis - Spectrograms - Soprasegmental phenomena.
      • Applications for speech processing.
    • Computational morphology
      • Generation and morphological analysis. Tabular lexica.
      • Techniques based on Finite State Automata.
    • Computational syntax
      • Part-of-speech tagging
      • Grammars for natural language
      • Parsing natural languages
      • Formal grammars for language analysis
        • Formal languages and natural language
        • Context-free grammars
        • Dependency grammars
        • Treebanks
    • Computational semantics
      • Lexical semantics: WordNet, FrameNet...
      • Word Sense Disambiguation
      • Distributional Semantic Models
      • Sentence semantincs and meaning representation

Applications:
  • Machine Translation
  • Question answering
  • Speaker diarisation/recognition
  • Stylometry and Dialectometry

Readings/Bibliography

Chapters extracted from:
- Lenci, A., Montemagni, S. and Pirrelli, V. (2005). Testo e computer. Carocci.
- D. Jurafsky and J.H. Martin (2008). Speech and Language Processing, 2nd ed., Prentice Hall.
- A. Clark, C. Fox, S. Lappin (2010). The Handbook of Computational Linguistics and Natural Language Processing, Blackwell Handbooks in Linguistics.

Teaching methods

Face-to-face classes and laboratory sessions for 30 hours.

Assessment methods

Oral colloquium.
It is compulsory to register for the exam using the online procedure.

Teaching tools

The course web site is the central point for any kind of information about the course. It contains the handouts and the readings discussed during the lessons as well as a rich software repository useful for laboratory practice.

A CD-ROM has been prepared for the students containing a complete computing environment to practice with the procedures proposed during the course. This tool will be used also in the laboratory sessions.

Links to further information

http://corpora.dslo.unibo.it/LingCompLM/

Office hours

See the website of Fabio Tamburini