| Abstract
|
We describe here some of the research unde … We describe here some of the research underly-ing the development of KANI (Knowledge As-sociates for Novel Intelligence), a hybrid system that combines large scale information extraction (IE) with knowledge representation (KR). The combination of these two technologies raises numerous research problems, such as an evalua-tion and understanding of the requirements that KR puts on IE and vice-versa, the identification of useful intermediate results in the process of transforming information from unstructured and massive collections into small and precise chunks suitable for automated reasoning, and how extend traditional explanation techniques to provide the ability to trace provenance of infor-mation through these transformations. nfor-mation through these transformations.
|
| Address
|
McLean, VA, USA, +
|
| Author
|
Christopher A. Welty +,
J. William Murdock +,
Paulo Pinheiro da Silva +,
Deborah L. McGuinness +,
David A. Ferrucci +,
Richard Fikes +
|
| Bibtype
|
inproceedings +
|
| Booktitle
|
Proceedings of the 2005 International Conference on Intelligence Analysis (IA 2005) +
|
| Key
|
KSL-05-05 +
|
| Modification dateThis property is a special property in this wiki.
|
1 May 2009 17:20:05 +
|
| Month
|
May +
|
| Paper
|
KSL-05-05.pdf +
|
| Relation
|
Inference web +
|
| Tag
|
Computer science +
|
| Title
|
Tracking Information Extraction from Intelligence Documents +
|
| Tr id
|
KSL-05-05 +
|
| Year
|
2005 +
|
| Categories |
Conference Paper,
Proceeding Paper,
Publication,
KSL Technical Report
|
