The original goal of this project was the extraction of certain information such as species, places, and people from texts downloaded from the Federal Register (https://www.federalregister.gov).
In the beginning, Anteater was developed as a Java command-line tool. However, version 2 was developed as a web application implemented using Spring MVC. So far, Anteater focuses on extracting information from Federal Register documents. These texts are mainly applications for permits, notices about given permits, etc.
Anteater aims to extract the following information:
You can download the final report of the Java command-line tool here.
Anteater has been developed at the Max Planck Institute for the History of Science (MPIWG) in Berlin by Julia Damerow in collaboration with Etienne Benson and Dirk Wintergrün.
Download Anteater from our files download page on Sourceforge.
Anteater v1.0 is released. Extract away!
The anteater comes as a webapp now. Deploy it in a servlet container and extract information from Federal Register documents!
Anteater will be available as web application soon. Check back later.