Description:

GESL is a C library for learning a string edit distance / similarity based on convex optimization. It is able to handle multi-class problems and also includes a classification library that allows to learn a sparse classifier from an edit similarity and to evaluate its performance on test data. GESL is open-source and distributed under GNU/GPL 3 license.

For more information / citation, refer to:

A. Bellet, A. Habrard and M. Sebban. Good edit similarity learning by loss minimization. Machine Learning, 2012, 89(1), 5-35.

http://perso.telecom-paristech.fr/~abellet/papers/edit_similarity_learning_mlj12.html

Changes to previous version:

Added datasets used in the experiments of the paper

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Agnostic

Data Formats: Various

Tags: Edit Distance, Metric Learning, Similarity Learning, String

Archive: download here

Other available revisons

Version	Changelog	Date
v1.01	Added datasets used in the experiments of the paper	May 15, 2015, 11:54:04
v1	Initial Announcement on mloss.org.	May 28, 2014, 09:42:21

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.