QLVL members - Yves Peirsman
Yves Peirsman studied Germanic Languages at the University of Leuven, with an Erasmus exchange at the University of Aarhus, Denmark, in the spring semester of 2003. After his graduation in 2004, he took the MSc in Speech & Language Processing at the University of Edinburgh, UK. He returned to the University of Leuven for a PhD project on the application of computational models of semantics to language variation and translation. Since he obtained his PhD in 2010, he has been working as a visiting post-doctoral scholar at Stanford University.
Phone: ++32 16 32 48 19
Fax: ++32 16 32 47 67
Surface mail: Department of Linguistics, Blijde-Inkomststraat 21 PO Box 03308, B-3000 Leuven, Belgium
Office: room 02.36 of the Faculty of Arts of the University of Leuven
Yves investigates distributional approaches to lexical semantics, which model the similarity in meaning between two words on the basis of the contexts in which these words occur. He uses these models for the identification of synonyms, both across different varieties of the same language and across languages.
The modelling of semantic similarity across language varieties is particularly useful in the study of language variation. Corpus-based measures of semantic similarity can help us identify, for example, American English synonyms to British English words and vice versa. Conversely, measures of semantic dissimilarity can aid the identification of words that are typical of a particular language variety.
Similarly, the modelling of semantic similarity across different languages can support a fully automatic extraction of word translations. The resulting models can deal with cross-lingual tasks like the identification of false friends (e.g., English kind and German Kind "child", or the modelling of selectional preferences in resource-poor languages.
The following publications are representative of Yves' research. The rest of his published work can be found in the QLVL publication list.
Peirsman, Y. and D. Geeraerts. 2006. "Metonymy as a prototypical category". Cognitive Linguistics 17(3): 269-316.
Peirsman, Y. and Sebastian Padó. 2010. "Cross-lingual Induction of Selectional Preferences with Bilingual Vector Spaces". In Proceedings of Human Language Technologies: The 11th Annual Conference of the North American Chapter of the Association for Computational Linguistics, Los Angeles, CA.
Peirsman, Y., D. Geeraerts and D. Speelman. 2010. "The Automatic Identification of Lexical Variation between Language Varieties". To be published in Natural Language Engineering.