Abstract We introduce OCELOT, a prototype system for automatically generating the “gist” of a web page by summarizing it. Although most text summarization research to date has ...
We describe recent extensions to the Ephyra question answering (QA) system and their evaluation in the TREC 2007 QA track. Existing syntactic answer extraction approaches for fact...
Molecular-biological annotation data is continuously being collected, curated and made accessible in numerous public data sources. Integration of this data is a major challenge in ...
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
Agents can freely migrate among open MASs in order to obtain resources or services not found locally. In this scenario, agent actions should be guided for avoiding unexpected behav...