In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forestto-string rule is capable of capturing nonsyntactic ...
Abstract. We propose a new matrix learning scheme to extend Generalized Relevance Learning Vector Quantization (GRLVQ). By introducing a full matrix of relevance factors in the dis...
In this work we show that entropy (H) and mutual information (MI) can be used as methods for extracting spatially localized features for classification purposes. In order to incre...
Liang Wu, Predrag Neskovic, Etienne Reyes, Elena F...
Caching, symmetries, and search with decomposition are powerful techniques for pruning the search space of constraint problems. In this paper we present an innovative way of effi...
Large screen display systems are common display systems nowadays. Especially projector-based PC cluster large screen display systems share most of large screen display system marke...