Description

The course gives an overview of this recent evolution, and handles the following aspects of it:

• historical motivation and background: pre-Chomskyan linguistics, pattern recognition, artificial intelligence
• applications: morpho-phonology, syntax, semantics, discourse
• linguistic issues: memory, modularity, representation
• data issues: scaling, automated/automatic annotation

Schedule

1. [February 20 2004]
   • Introduction
     Historical background; originating research fields; basic research questions and issues
   • WEKA installation
   • Classic ML (1): top-down induction of decision trees

2. [February 27 2004]
   • ML for anaphora resolution - Powerpoint slides
     
   • Guest lecture by Véronique Hoste
   • Classic ML (2): k-NN classification & memory-based learning

3. [March 5 2004]
   • ML for morphology and phonology
     
   • Diminutive formation; word pronunciation; morphological analysis
   • POS tagging; chunking; function tagging
   • Classic ML (3): Rule induction

4. [March 12 2004]
   • ML for shallow parsing and lexical semantics
     POS tagging; NP chunking; Word sense disambiguation
   • Classic ML (4): Naive Bayes
     Spam filtering

5. [March 19 2004]
   • ML for discourse - Powerpoint slides; Class exercises and solutions
     Shallow understanding of users in dialogue systems
   • Classic ML (5): Voting, stacking, boosting

6. [March 26 2004]
   • Major issues (1): Memory
     Computation versus memory; forgetting exceptions
   • Classic ML (6): Artificial neural networks

7. [April 2 2004]
   • Major issues (2): Representation
     Domain knowledge; feature selection and construction
   • Classic ML (7): Genetic search

8. [April 23 2004]
   • Classic ML (8): Unsupervised learning; PDF slides
   • Guest lecture by Erik Tjong Kim Sang

9. [April 30 2004]
   • Major issues (3): Modularity
     Minimal description length principle; software engineering
   • Major issues (4): More data
     Learning curves; automatic or machine-aided annotation
   • End assignment, roundup

Links

• LT-World
  maintained at DFKI
• Machine Learning Resources Page
  maintained by David W. Aha
• MLnet Machine Learning Archive
  MLnet Online Information System
• List of Online ML Resources
  maintained by Gerhard Widmer at the ML Group at OFAI (Vienna, Austria)
• SIGNLL
  ACL's Special Interest Group on Natural Language Learning

Relevant literature

• Jurafsky, D., and Martin, J. (2000). Speech and language processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice-Hall.
• Mitchell, Tom (1997). Machine Learning. McGraw Hill.
• Manning, C., and Schütze, H. (1999). Foundations of Statistical Natural Language Processing. MIT Press.
• Witten, I., and Frank, E. WEKA Tutorial.