Cross-lingual Induction of Selectional Preferences with Bilingual Vector Spaces

We describe a cross-lingual method for the induction of selectional preferences for resourcepoor languages, where no accurate monolingual models are available. The method uses bilingual vector spaces to "translate" foreign language predicate-argument structures into a resource-rich language like English. The only prerequisite for constructing the bilingual vector space is a large unparsed corpus in the resource-poor language, although the model can profit from (even noisy) syntactic knowledge. Our experiments show that the cross-lingual predictions correlate well with human ratings, clearly outperforming monolingual baseline models.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Yves Peirsman, Sebastian Padó
• Keywords: Accurate Monolingual Models, Bilingual Vector, Computational Linguistics, Monolingual Baseline Models, NAACL 2010