Building NLG systems, in particular statistical ones, requires parallel data (paired inputs and outputs) which do not generally occur naturally. In this paper, we investigate the ...
Automatic recognition of named entities such as people, places, organizations, books, and movies across the entire web presents a number of challenges, both of scale and scope. Da...
Casey Whitelaw, Alexander Kehlenbeck, Nemanja Petr...
Software tools are used to compare multiple versions of a textual document to help a reader understand the evolution of that document over time. These tools generally support the ...
Noun phrases carry much of the information in a text. Systems that attempt to acquire knowledge from text must first decompose complex noun phrases to get access to that informatio...
The Tarragon Consulting team participated in the primary task of the TREC 2003 Genomics Track. We used a combination of knowledge-engineering and corpus analysis to construct sema...