In this paper, we propose a versatile disambiguation approach which can be used to make explicit the meaning of structure based information such as XML schemas, XML document struc...
We show how web mark-up can be used to improve unsupervised dependency parsing. Starting from raw bracketings of four common HTML tags (anchors, bold, italics and underlines), we ...
Valentin I. Spitkovsky, Daniel Jurafsky, Hiyan Als...
Vocabularies to describe research findings are needed to effectively use scientific databases. As understanding of data evolves, scientists need tools for extending the vocabulari...
Josiah Johnston, Arpun Nagaraja, Harry Hochheiser,...
Web object is defined to represent any meaningful object embedded in web pages (e.g. images, music) or pointed to by hyperlinks (e.g. downloadable files). Users usually search for...
This paper explores the potential for annotating and enriching data for low-density languages via the alignment and projection of syntactic structure from parsed data for resource...