We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
The present paper presents the structure of a cross-linguistic database of production data. The database contains annotated texts collected from a sample of fifteen different langu...
The Varro toolkit is a system for identifying and counting a major class of regularity in treebanks and annotated natural language data in the form of treestructures: frequently r...
We present a framework to extract the most important features (tree fragments) from a Tree Kernel (TK) space according to their importance in the target kernelbased machine, e.g. ...
Abstract. This work proposes a family of language-independent semantic kernel functions defined for individuals in an ontology. This allows exploiting wellfounded kernel methods fo...