This paper describes a newly created text corpus of news articles that has been annotated for cross-document co-reference. Being able to robustly resolve references to entities ac...
David Day, Janet Hitzeman, Michael L. Wick, Keith ...
We present a new method for blind document bleed through removal based on separate Markov Random Field (MRF) regularization for the recto and for the verso side, where separate pri...
—Because of writing styles of different individuals, some of the text-lines may be curved in shape. For recognition of such text-lines, their proper alignment is necessary. In th...
Classification of documents by genre is typically done either using linguistic analysis or term frequency based techniques. The former provides better classification accuracy than...
There is an asymmetry in many tangible interfaces: while phicons can be used to manipulate digital information, the reverse is often not possible ? the digital world cannot push b...