NERSimString is a Java reimplementation of the SimString algorithm proposed by Naoaki Okazaki ( http://www.chokkan.org/software/simstring ).

SimString is an algorithm for approximate Search (Fuzzy Search). In this project we present 3 different approaches based on Approximate Dictionary Matching Algorithm that uses similarity measures for the retrieval of Named Entities.

This re-implementation is oriented to the task of Name entity annotation, and it is implemented in such a way that adding extra structures for Name entity signatures should be rather straight forward.

src folder contains all the java source code of NERSimString
lib contains all the dependancies of NERSimString
doc contains the latex documentation of the project
ProjectReport.pdf is a short explanation of the project objectives,solution and conclutions

Examples are provided in the folder src/Examples

Feel free to leave an email in one of the following addresses:

dav.alejandro@gmail.com
sciddi@coli.uni-sb.de
nfadaei@coli.uni-sb.de
moinuddinmushirul@gmail.com