Increasingly, companies recognize that most of their important information does not exist in relational stores but in documents. For a long time, textual information has been rela...
Statistical topic models provide a general data-driven framework for automated discovery of high-level knowledge from large collections of text documents. While topic models can p...
Chaitanya Chemudugunta, Padhraic Smyth, Mark Steyv...
Although detecting text lines in machine printed documents is typically considered a solved problem, it is still a challenge to segment handwritten text lines in the general sense...
Sheffield's participation in the inaugural Arabic cross language track is described here. Our goal was to examine how well one could achieve retrieval of Arabic text with the...