When address reference streams exhibit high degrees of spatial and temporal locality, many of the higher order address lines carry redundant information. By caching the higher ord...
The basic aim of the model proposed here is to automatically build semantic metatext structure for texts that would allow us to search and extract discourse and semantic informati...
This paper describes the experience of QAST 2009, the third time a pilot track of CLEF has been held aiming to evaluate the task of Question Answering in Speech Transcripts. Four ...
Jordi Turmo, Pere Comas, Sophie Rosset, Olivier Ga...
A framework is presented for discovering partial duplicates in large collections of scanned books with optical character recognition (OCR) errors. Each book in the collection is r...
To announce the ownership of video such as TV programs, the owner usually embeds his logo into the programs in a visible way. Since the logo and its position are usually fixed in...