Document Selection for Extracting Entity and Relationship Instances of Terrorist Events
In this chapter, we study the problem of selecting documents so as to extract terrorist event information from a collection of documents. We represent an event by its entity and relation instances. Very often, these entity and relation instances have to be extracted from multiple documents. We therefore define an information extraction (IE) task as selecting documents and extracting from which entity and relation instances relevant to a user-specified event (aka domain specific event entity and relation extraction). We adopt domain specific IE patterns to extract potentially relevant entity and relation instances from documents, and develop a number of document ranking strategies using the extracted instances to address this extraction task. Each ranking strategy (aka pattern-based document ranking strategy) assigns a score to each document, which estimates the latter's contribution to the gain in event related instances. We conducted experiments on two document collection datasets constructed using two historical terrorism events. Experiments showed that our proposed patternbased document ranking strategies performed well on the domain specific event entity and relation extraction task for document collections of various sizes.
Databases and Information Systems | Defense and Security Studies | Numerical Analysis and Scientific Computing
Data Management and Analytics
Terrorism Informatics: Knowledge Management and Data Mining for Homeland Security
Chen, Hsinchun; Reid, Edna; Sinai, Joshua; Silke, Andrew; Ganor, Boaz
City or Country
SUN, Zhen; LIM, Ee Peng; CHANG, Kuiyu; Suryanto, Maggy Anastasia; and Gunaratna, Rohan Kumar.
Document Selection for Extracting Entity and Relationship Instances of Terrorist Events. (2008). Terrorism Informatics: Knowledge Management and Data Mining for Homeland Security. 18, 309-346. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/848