Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ m...
We have combined an artificial neural network (ANN) character classifier with context-driven search over character segmentation, word segmentation, and word recognition hypotheses...
Near-term spoken language systems willlikely be limited in their interactive capabilities. To design them, we shall need to model how the presence or absence of speaker interactio...
A central issue in bilingual research concerns the extent to which linguistic representations in the two languages are processed independently of each other. This paper reports th...