Traditional research on spelling correction in natural language processing and information retrieval literature mostly relies on pre-defined lexicons to detect spelling errors. Bu...
PowerAqua1 is a Question Answering system, which takes as input a natural language query and is able to return answers drawn from relevant semantic resources found anywhere on the...
Vanessa Lopez, Victoria S. Uren, Marta Sabou, Enri...
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
We consider the problem of a user querying semistructured data such as RDF without knowing its structure. In these circumstances, it is helpful if the querying system can perform a...
Carlos A. Hurtado, Alexandra Poulovassilis, Peter ...
Web search quality can vary widely across languages, even for the same information need. We propose to exploit this variation in quality by learning a ranking function on bilingua...