Method:

This web site is best viewed in Google Chrome and Internet Explorer.

BioSSES computes similarity of biomedical sentences by utilizing WordNet as the general domain  ontology and UMLS as the biomedical domain specific ontology.

We allow you to compute sentence similarity with the following methods:

Qgram [0-1]
Wordnet [0-1]
UMLS [0-1]
Paragraph Vector [0-1]
Combined Ontology (Wordnet and UMLS) [0-1]
Supervised Approach [0-4]

For citing this study, please use:

Gizem Soğancıoğlu, Hakime Öztürk, Arzucan Özgür; BIOSSES: a semantic sentence similarity estimation system for the biomedical domain. Bioinformatics 2017; 33 (14): i49-i58. doi: 10.1093/bioinformatics/btx238


BioSSES is a set of Java codes for computing semantic sentence similarity, developed by Gizem Sogancioglu, Hakime Ozturk and Arzucan Ozgur, in the Department of Computer Engineering, Bogazici University.

BioSSES is open-source software made available under the terms of the The GNU Common Public License v.3.0. You are free to use the code under those terms.