The major limitation in bilingual latent semantic analysis (bLSA) is the requirement of parallel training corpora. Motivated by semi-supervised learning, we propose a clusterbased...
In the domain of XML authoring, there have been many tools to help users to edit XML documents. These tools make it easier to produce complex documents by using such technologies ...
Non-linear warping appears in document images when captured by a digital camera or a scanner, especially in the case that these documents are digitized bounded volumes. Arbitraril...
Basilios Gatos, Ioannis Pratikakis, Konstantinos N...
We study the analysis problem of XPath expressions with counting constraints. Such expressions are commonly used in document transformations or programs in which they select porti...
This paper describes a tool for recombining the logical structure from an XML document with the typeset appearance of the corresponding PDF document. The tool uses the XML represe...
Matthew R. B. Hardy, David F. Brailsford, Peter L....