Aline Villavicencio

Postdoctoral Researcher

Contact Details

Research Interests

I'm a Researcher at the Natural Language and Information Processing Group, in the Computer Laboratory. I'm currently working on the Multiword Expression Project, with Ann Copestake. This project investigates multiword expressions, like idioms and verb-particle constructions and develops treatments and resources for them.

I recently completed my PhD entitled The Acquisition of a Unification-Based Generalised Categorial Grammar, where I investigate the acquisition of grammatical knowledge from a corpus of child-directed transcribed speech, using a model of Universal Grammar encoded as a Unification-Based Generalised Categorial Grammar, embedded in a typed default inheritance hierarchy, implemented using the LKB system. A description of the learning system and some experiments perfomed can be found in The Acquisition of a Unification-Based Generalised Categorial Grammar, The acquisition of word order by a computational learning system, and Grammatical Learning Using Unification-Based Generalised Categorial Grammars. The results obtained in experiments demonstrate that the resulting learner can successfully acquire constituent order parameters even in the presence of noise in the mapping to logical forms. This research was done under the supervision of  Ted Briscoe.

Before doing the PhD, I did the MPhil course in Computer Speech and Language Processing, in the Engineering Department. My main interests are in Natural Language Processing and Computational Linguistics, more specifically in grammar engineering, grammar development with lexicalised linguistic formalisms and computational language acquisition.

Current and Recent Activities

• ACL-2004 Workshop on Multiword Expressions: Integrating Processing
  with Takaaki Tanaka, Anna Korhonen and Francis Bond

• Computer Speech and Language Special Issue on Multiword Expressions
  with Anna Korhonen, Francis Bond and Diana McCarthy
  SUBMISSION DEADLINE MAY 5, 2004

• ACL-2003 workshop on Multiword Expressions: Analysis, Acquisition and Treatment

Selected Papers

• Villavicencio, A. Verb-Particle Constructions and Lexical Resources. In Francis Bond, Anna Korhonen, Diana McCarthy and Aline Villavicencio, eds. Proceedings of the ACL 2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment, p. 57—64. Sapporo, 2003.

• Terkourafi, M. and Villavicencio, A. Toward a formalisation of speech-act functions of questions in conversation. In Proceedings of the 2nd CoLogNET-ElsNET Symposium: Questions and Answers: Theoretical and Applied Perspectives. Amsterdam, 2003.

• Buttery, P. and Villavicencio, A. Language Acquisition and the Universal Grammar. Proceedings of AMLaP'2003: Architectures and Mechanisms for Language Processing. Glasgow, 2003.

• Villavicencio, A. Verb-Particle Constructions in the World Wide Web. Proceedings of the ACL-SIGSEM Workshop on the Linguistic Dimensions of Prepositions and their use in Computational Linguistics Formalisms and Applications. Toulouse, France, 2003.

• Villavicencio, A. and A. Copestake. Verb-particle constructions in a computational grammar of English. In Jongbok Kim and Stephen Wechsler, eds., Proceedings of the Ninth International Conference on Head-Driven Phrase Structure Grammar. Kyung-Hee University, Seoul. Stanford: CSLI Publications. Available at: http://cslipublications.stanford.edu/HPSG/3/hpsg02.htm .
• Copestake, A.,  F. Lambeau, A. Villavicencio, F. Bond, T. Baldwin, I. A. Sag and D. Flickinger. Multiword expressions: linguistic precision and reusability. Third conference on Language Resources and Evaluation (LREC-2002), p. 1941—1947. Las Palmas, Canary Islands, 2002.
• Baldwin, T. and A. Villavicencio. Extracting the unextractable: A case study on verb-particles. In Proc. of the 6th Conference on Natural Language Learning (CoNLL-2002), Taipei, Taiwan, 2002.
• Villavicencio, A. Learning to distinguish PP arguments from adjuncts. In Proc. of the 6th Conference on Natural Language Learning (CoNLL-2002), Taipei, Taiwan, 2002.
• Villavicencio, A., The Acquisition of a Unification-Based Generalised Categorial Grammar. Thesis published as Technical Report UCAM-CL-TR-533, Computer Laboratory, University of Cambridge, 2001.

• Villavicencio, A., The acquisition of word order by a computational learning system. Proceedings of the 2nd Learning Language in Logic Workshop, Lisbon, 2000.

• Villavicencio, A., The Use of Default Unification in a System of Lexical Types. Proceedings of the Workshop on Linguistic Theory and Grammar Implementation, Birmingham, 2000.

• Villavicencio, A., Grammatical Learning Using Unification-Based Generalised Categorial Grammars. Proceedings of AMLaP' 2000: Architectures and Mechanisms for Language Processing, Leiden, 2000.

• Villavicencio, A., The Acquisition of a Unification-Based Generalised Categorial Grammar. Proceedings of Cluk, Brighton, 2000.

• Villavicencio, A., Representing a System of Lexical Types Using Default Unification. Proceedings of EACL, Bergen, 1999.

• Villavicencio, A., Building a Wide-Coverage Combinatory Categorial Grammar. MPhil Thesis, University of Cambridge, 1997.

• Villavicencio, A., Viccari, R.M., "Evaluating Stochastic Past-of-Speech Taggers for the Portuguese Language", Second Meeting of the Computational Processing of Spoken and Written Portuguese Language, 1996.

• Villavicencio, A., Marques, N.M., Lopes, J.G.P.,Villavicencio, F., "Part-of-Speech tagging for Portuguese Texts",(ed.) Jacques Wainer and Ariadne Carvalho:Advances in Artificial Intelligence: Proceedings of the of the XII Brazilian Symposium on Artificial Intelligence , 1995. Lecture Notes in Artificial Intelligence 991, pp. 323-332. Springer Verlag.

Some Useful Links

• The NLP Archive (on-line papers)
• Association for Computational Linguistics
• Colibri Home Page
• Multiword Expression Project
• Multiword Expression Project Bibliography
• Categorial Grammar Home Page