The topic of this semester's course will be the automatic learning of morphology from corpora, with a particular focus on unsupervised methods. There have been a number of papers on this topic over the past few years. A few links to these are listed below:

• Jacquemin, Christian. 1997. "Guessing morphology from terms and corpora." SIGIR'97, pp. 156-167, Philadelphia, PA.
• Pieter Theton, Ian Cloete. 1997. "Automatic Acquisition of Two-Level Morphological Rules". ANLP97, Washington, DC.
• John Goldsmith. 2001. "Unsupervised Acquisition of the Morphology of a Natural Language". Computational Linguistics.
• Schone, P. and D. Jurafsky. (2000) "Knowledge-free induction of morphology using latent semantic analysis." Proc. of the Computational Natural Language Learning Conference, Lisbon, pp. 67-72.
• Schone, Patrick and Daniel Jurafsky. 2001. "Knowlege-Free Induction of Inflectional Morphologies." Proceedings of the North American Chapter of the Association for Computational Linguistics.
• Schone, Patrick. 2001. Toward Knowledge-Free Induction of Machine-Readable Dictionaries. Ph.D. Dissertation, University of Colorado at Boulde. Gzipped PDF
• David Yarowsky and Richard Wicentowski. 2001. "Minimally supervised morphological analysis by multimodal alignment." Proceedings of ACL-2000, Hong Kong, pages 207-216.
• Richard Wicentowski. 2002. Modeling and Learning Multilingual Inflectional Morphology in a Minimally Supervised Framework. PhD Dissertation, Johns Hopkins University.
• Utpal Sharma, Jugal Kalita, and Rajib Das. "Unsupervised Learning of Morphology for Building Lexicon for a Highly Inflectional Language" Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 1-10.
• Matthew G. Snover, Gaja E. Jarosz and Michael R. Brent. 2002. "Unsupervised Learning of Morphology Using a Novel Directed Search Algorithm: Taking the First Step" Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 11-20.
• Matthew Snover and Michael Brent. 2001. "A Bayesian Model for Morpheme and Paradigm Identification." Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-2001), pages 482-490. PDF
• Mathias Creutz and Krista Lagus. 2002. "Unsupervised Discovery of Morphemes" Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 21-30.
• Sylvain Neuvel and Sean A. Fulop. 2002. "Unsupervised Learning of Morphology Without Morphemes"Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 31-40.
• Mikhail Belkin and John Goldsmith. 2002. "Using eigenvectors of the bigram graph to infer morpheme identity"Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 41-47.
• Marco Baroni, Johannes Matiasek and Harald Trost. 2002. "Unsupervised discovery of morphologically related words based on orthographic and semantic similarity" Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 48-57.
• Adam Albright and Bruce Hayes. 2002. "Modeling English Past Tense Intuitions with Minimal Generalization"Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pp. 58-69.
• Howard Johnson, Joel Martin. 2003. "Unsupervised Learning of Morphology for English and Inuktitut". Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics.
• Some recent papers on the old "past-tense" debate from TRENDS in Cognitive Science, 2002:
  • Pinker & Ullman A
  • McClelland & Patterson A
  • Pinker & Ullman B
  • McClelland & Patterson B
• Alexander Clark. 2001. "Learning morphology with pair hidden markov models." Proceedings of the ACL Student Workshop 55-60.
• Alexander Clark (2001) "Partially Supervised Learning of Morphology with Stochastic Transducers," Proceedings of Natural Language Processing Pacific Rim Symposium (NLPRS) 2001, November 2001, Tokyo. [Postscript][PDF]
• Alexander Clark (2002). "Memory-based learning of morphology with stochastic transducers." ACL 2002. 513-520 PDF

There will be no textbook for this course.

The course will consist of readings, including those listed above, discussion of the readings, and working in groups to implement some of the ideas discussed in the readings. Depending upon the composition of the class, the knowledge of other languages, and the availability of corpora, we may work with languages other than English.

Interspersed with this we will also look at some more descriptive work on morphology. Despite the impressive advances in this area over the past few years, the problem is far from solved, and there are a number of forms of morphological expression that are not readily handled by the current techniques. Given time enough in the course, we may investigate how such types of morphology might be handled.

A tentative syllabus is here.

A note on the Computational Linguistics Lab Machines