Publications

2004

• Gaustad, Tanja (2004): Linguistic Knowledge and Word Sense Disambiguation. [ps, pdf] Summary [ps, pdf].
  PhD thesis, Alfa-Informatica, University of Groningen, Groningen. [bibtex entry]
• Gaustad, Tanja (2004): "A Lemma-Based Approach to a Maximum Entropy Word Sense Disambiguation System for Dutch". [ps, pdf]
  Proceedings of the 20th International Conference on Computational Linguistics (Coling 2004), Geneva, Switzerland, pp. 778-784. [bibtex entry]

2003

• Gaustad, Tanja (2003): "The Importance of High Quality Input for WSD: An Application-Oriented Comparison of Part-of-Speech Taggers". [ps, pdf]
  Proceedings of the Australasian Language Technology Workshop (ALTW 2003), Melbourne, Australia, pp. 65-72. [bibtex entry]
• Gaustad, Tanja (2003 ed.): Computational Linguistics in the Netherlands 2002. Selected Papers from the Thirteenth CLIN Meeting.
  Number 47 in "Language and Computers: Studies in Practical Linguistics", Rodopi: Amsterdam. [bibtex entry]

2002

• Gaustad, Tanja and Gertjan van Noord (2002): "Lexically Sensitive Disambiguation Techniques". [pdf]
  In BCN Annual Report 1999-2000-2001, chapter 6-13.
• Leonoor van der Beek, Gosse Bouma, Jan Daciuk, Tanja Gaustad, Robert Malouf, Gertjan van Noord, Robbert Prins, Begoña Villada (2002): "Algorithms for Linguistic Processing". [ps, pdf]
  Progress Report NWO PIONIER Project.
• Gaustad, Tanja and Gosse Bouma (2002): "Accurate Stemming of Dutch for Text Classification". [ps, pdf]
  In Computational Linguistics in the Netherlands 2001, pp. 104-117. [bibtex entry]

2001

• Gaustad, Tanja (2001): "Statistical Corpus-Based Word Sense Disambiguation: Pseudowords vs. Real Ambiguous Words". [ps, pdf]
  In Companion Volume to the Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL/EACL 2001) -- Proceedings of the Student Research Workshop, Toulouse, France, pp. 61-66. [bibtex entry]
• Gaustad, Tanja (2001): "Lexically Sensitive Disambiguation Techniques, Research Proposal". [ps, pdf]
  Internal first year report, CLCG, University of Groningen.

2000

• Gaustad, Tanja (2000): "Extraktion und Verifikation von Subkategorisierungsmustern für französische Verben". [ps, pdf]
  In Ulrich Heid, Stefan Evert, Egbert Lehmann, Christian Rohrer (eds.), Proceedings of the Ninth EURALEX International Congress, EURALEX 2000, Stuttgart, Germany, August 8-12, 2000, 611-617. [bibtex entry]

1999

• Gaustad, Tanja (1999, unpublished): "La polysémie de trois verbes cognitifs (apprendre, connaître, savoir) et leur désambiguïsation automatique à l'aide de corpus informatisés" (The polysemy of three cognitive verbs (apprendre, connaître, savoir) and their automatic disambiguation with the help of corpora).
  MA Thesis, University of Basel, supervised by Prof. G. Lüdi (Institute of romance languages and literature, University of Basel) and Dr. U. Heid (IMS, University of Stuttgart). [bibtex entry]

Presentations

2004

• "Linguistic Knowledge and Word Sense Disambiguation." [ps, pdf], CLCG Linguistics Symposium, 8 October 2004, Groningen.
• "A Lemma-based Approach to a Maximum Entropy Word Sense Disambiguation System for Dutch." [ps, pdf] Coling 2004, 26 August 2004, Geneva.
• "An Investigation into the Use of Linguistics for Word Sense Disambiguation of Dutch." [ps] BCN PhD Retreat, April 2004, Odoorn.

2003

• "The Importance of High Quality Input for WSD: An Application-Oriented Comparison of Part-of-Speech Taggers." [ps, pdf] ALTW 2003, 10 December 2003, Melbourne.
• Poster presentation "Lexically Sensitive Disambiguation Techniques." [ps] BCN poster afternoon, January 2003, Groningen.

2002

• "The Best of Two Worlds: Word Sense Disambiguation Using Statistics and Linguistics." [ps] BCN PhD Retreat, April 2002, Doorwerth.
• "Word Sense Disambiguation as Classification Problem." (invited) [ps, pdf] Potchefstroomse Universiteit vir Christelike Hoër Onderwys, March 2002, Potchefstroom, South Africa.

2001

• "Accurate Stemming and Email Classification." [ps, pdf] CLIN 2001 (Computational Linguistics in the Netherlands), University of Twente, November 2001, Enschede.
• "Statistical Corpus-Based Word Sense Disambiguation: Pseudowords vs. Real Ambiguous Words." [ps, pdf] ACL Student Research Workshop, July 2001, Toulouse.
• Poster presentation "Word Sense Disambiguation Using a Naive Bayes Classification Algorithm and Pseudowords." [ps] BCN poster afternoon, January 2001, Groningen.

2000

• "Extraction and Verification of Subcategorization Patterns for French Verbs." [ps] EURALEX, August 2000, Stuttgart.
• "Extraction and Verification of Subcategorization Patterns for French Verbs: Illustration of an Approach." Humanities Computing Department, University of Groningen, February 2000, Groningen.

1999

• "Datenbeschaffung für den Aufbau von syntaktischen Wörterbüchern für die Sprachverarbeitung: Methoden für die Arbeit mit Deutsch und Französisch." With Ulrich Heid. 4. Internationale Tagung zum romanisch-deutschen und innerromanischen Sprachvergleich, October 1999, Leipzig.