This paper presents the QALL-ME benchmark, a multilingual resource of annotated spoken requests in the tourism domain, freely available for research purposes. The languages curren...
Elena Cabrio, Milen Kouylekov, Bernardo Magnini, M...
Internet content today is about 80% text-based. No matter static or dynamic, the information is encoded and presented as multilingual, unstructured natural language text pages. As ...
Pavlin Dobrev, Albena Strupchanska, Galia Angelova
This paper presents an approach for the integration of domain related elements and operational semantics into collaborative environments based on visual languages. This integratio...
Niels Pinkwart, Heinz Ulrich Hoppe, Katrin Ga&szli...
We explore a linguistically motivated approach to the problem of recognizing speculative language ("hedging") in biomedical research articles. We describe a method, whic...
This paper proposes and compares four cross-lingual and bilingual automatic speech recognition techniques under the constraints of limited memory size and CPU speed. The first thr...