Topics in prior-art patent search are typically full patent applications and relevant items are patents often taken from sources in different languages. Cross language patent retr...
The LOGON MT demonstrator assembles independently valuable general-purpose NLP components into a machine translation pipeline that capitalizes on output quality. The demonstrator ...
Abstract One of the main hurdles to improved CLIR effectiveness is resolving ambiguity associated with translation. Availability of resources is also a problem. First we present a ...
Aligned corpora are often-used resources in CLIR systems. The three qualities of translation corpora that most dramatically affect the performance of a corpus-based CLIR system are...
Ontology as a knowledge base can provide different reasoning tasks, e.g. to check consistency of the ontology or to check whether a resource is instance of a concept or not. In thi...