Suggested Upper Merged Ontology (SUMO)
    [Home | Browse | Download | Publications | Tools | What‘s New | About]

    The Suggested Upper Merged Ontology (SUMO) and its domain ontologies form the largest formal public ontology in existence today. They are being used for research and applications in search, linguistics and reasoning. SUMO is the only formal ontology that has been mapped to all of the WordNet lexicon. SUMO is written in the SUO-KIF language. SUMO is free and owned by the IEEE. The ontologies that extend SUMO are available under GNU General Public License. Adam Pease is the Technical Editor of SUMO.

    		 Find an English word and its corresponding formal term in SUMO:
    English Word: 

    Features
    • Mappings to all of WordNet
    • Language generation templates for Hindi, Chinese, Italian, German, Czech and English
    • Tools for browsing, editing, inferencing and NLP with SUMO are found in the SigmaKEE (source, api, docker image), SUMOjEdit(source) and SigmaNLP (source, api, docker image) systems
    • Largest free, formal ontology available, with ~25,000 terms and ~80,000 axioms when all domain ontologies are combined. These consist of SUMO itself, the MId-Level Ontology (MILO), and ontologies of Communications, Countries and regions, Distributed computing and User interfaces, Economy, Finance, Automobiles and Engineering components, Food, Dining, Sports, Shopping catalogs and Hotels, Geography, Government and Justice, Language taxonomy, Law, Media, Medicine (and Anatomy), Music, Military (General, Devices, Processes, People), North American Industrial Classification System, People and their Emotions, Physical elements, Transnational issues, Transportation and its Details, Viruses, Weather, world airports, and weapons of mass destruction. See also a large amount of instance content from DBPedia about people and the YAGO, project which includes millions of facts from Wikipedia merged with SUMO, and an initial merge of the Mondial geographical data with SUMO. The Open Biomedical Ontologies are lightly mapped to SUMO.
    • Richly axiomatized, not just a taxonomy. All terms are formally defined. Meanings are not dependent on a particular inference implementation.

    Documentation and other resources

    • An introductory talk, YouTube Channel, podcasts and a blog about SUMO and Sigma
    • Some good examples that show why simple search isn't enough and that we need inference to synthesize information from multiple sources
    • look at historical versions of SUMO
    • static documentation pages
    • We ask that people working with SUMO cite our primary paper and book in any publications
    • Conformance testing for SUMO
    • SUMO in TPTP for use with provers such as E prover and Vampire - TPTP FOF (SUMO upper level only, SUMO+MILO, all) and Typed First-order form with Arithmetic (SUMO upper level only, SUMO+MILO, all)
    • Translation of the upper level of SUMO into a Neo4J graph, and all of SUMO and its domain ontologies into a Neo4j graph. Translation of SUMO into OWL and WordNet 3.0 in OWL
    • WordNet in TPTP format
    • Some thoughts on an ontology development process and ontology development pitfalls
    • An introduction to resolution theorem proving
    • Frequently asked questions
    • A word sense frequency analysis based on WordNet SemCor that can be used for simple word sense disambiguation. This was done on WN 1.6 but could be rerun with the automatic remappings to 2.0
    • A very big graph of the taxonomy in SUMO v 1.75 (too big to display in a browser, download and view in a drawing application)

    Order a copy of the book "Ontology: A Practical Guide" for $25+tax/domestic US shipping (international customers should email me first to get shipping costs)

    Using SUMO on a project already? Some 5000 unique domains use the online Sigma browser every month. Please consider making a donation to help us continue providing support and improvements.

    Webmaster