One may need to build a statistical parser for a new language, using only a very small labeled treebank together with raw text. We argue that bootstrapping a parser is most promis...
Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web’s natural language text. Knowledge-based weak supervision, using structured...
Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke S....
Abstract--User-system interaction is sometimes a cumbersome element of non-textual information access. Image retrieval systems now incorporate various interaction mechanisms. Howev...
The SWRLTab is a development environment for working with SWRL rules in Protégé-OWL. It supports the editing and execution of SWRL rules. It also provides mechanisms to allow int...
Martin J. O'Connor, Samson W. Tu, Csongor Nyulas, ...
Aggregate ranking tasks are those where documents are not the final ranking outcome, but instead an intermediary component. For instance, in expert search, a ranking of candidate ...