The TIPSTER Text Program incorporated new research efforts and fostered improvements to current developments. Under Phase III, the program continued to advance the state-of-the-art for the underlying technologies of Document Detection and Information Extraction.
TIPSTER research efforts focused on the following areas: 数据挖掘研究院
-
Text summarization - an enhancement in information extraction and information retrieval to develop methods and algorithms to produce a summary for each document of interest or a single summary of multiple documents in a collection of interest. 数据挖掘研究院
-
Merging search results - develop the means to merge results from different search engines while maintaining a relevance ranking for the retrieved information or to fuse the retrieved information with other items. 数据挖掘研究院
-
Coreference resolutions - develop algorithms to resolve multiple text references to the same entity to better understand relationships among entities mentioned in a document.
-
Customization methods - develop effective ways for a system administrator or end-user to port tools and techniques shown to work in one language or domain to other languages or domains. 数据挖掘研究院
-
Multilingual capability enhancements.
-
Improvements in natural language processing capabilities.
-
Improvements in recall and precision for document detection (routing and retrieval) and information extraction algorithms. 数据挖掘研究院
