The Linguistica Project

Aris Xanthos, Yu Hu, and John Goldsmith. Exploring variant definitions of pointer length in MDL. In Papers from the 2006 SIGPHON meeting (New York).

Yu Hu, Irina Matveeva, John Goldsmith, and Colin Sprague.The SED heuristic for morpheme discovery: a look at Swahili. In Workshop on Psychocomputational Models of Human Language Acquisition (ACL-2005), Ann Arbor MI.

Yu Hu, Irina Matveeva, John Goldsmith, and Colin Sprague. Using morphology and syntax together in unsupervised learning. In Workshop on Psychocomputational Models of Human Language Acquisition (ACL-2005), Ann Arbor MI.

John Goldsmith, Yu Hu, Irina Matveeva, and Colin Sprague. A heuristic for morpheme discovery based on string edit distance. Technical report TR-2005-04, Department of Computer Science, University of Chicago.

Goldsmith, John and Yu Hu. 2004. From Signatures to Finite State Automata. Midwest Computational Linguistics Colloquium. Bloomington IN. June 25-26. Technical report TR-2005-05, Department of Computer Science, University of Chicago.

Goldsmith, John. (ms. 2004) An algorithm for the unsupervised learning of morphology . To appear in Natural Language Engineering.

Belkin, Mikhail and John Goldsmith. 2002. Using eigenvectors of the bigram graph to infer morpheme identity. Proceedings of the Morphology/Phonology Learning Workshop of ACL-02. Association for Computational Linguistics.

Goldsmith, John. 2001. Unsupervised Learning of the Morphology of a Natural Language. Computational Linguistics. 153-189.

Goldsmith, John, Derrick Higgins, and Svetlana Soglasnova. 2001. Automatic Language-Specific Stemming in Information Retrieval. In Carol Peters (ed.). Cross-Language Information Retrieval and Evaluation: Proceedings of the CLEF 2000 Workshop, pages 273-283. Lecture Notes in Computer Science. Springer Verlag.

Goldsmith, John. 2000. Linguistica: An Automatic Morphological Analyzer.The Proceedings from the Main Session of the Chicago Linguistic Society's Thirty-sixth Meeting. Arika Okrent and John Boyle (eds.) 36-1.

Goldsmith, John and Tom Reutter. 1999. Automatic Collection and Analysis of German Compounds. In The Computational Treatment of Nominals: Proceedings of the Workshop COLING-ACL '98, edited by Frederica Busa, Inderjeet Mani and Patrick Saint-Dizier, pp. 61-69. Montreal: COLING-ACL.


Slides from June 8, 2006 SIGPHON meeting in New York City: ppt Variant definitions of pointer length in MDL, by Aris Xanthos, Yu Hu, and John Goldsmith

Slides from January 7, 2005 presentation at Linguistics Society of America: html Automatic learning of morphological structure, with Colin Sprague and Yu Hu.

Slides from February 7, 2003 presentation at CS Department, University of Chicago: ppt html Learning linguistic structure.