A '''semantic similarity network''' ('''SSN''') is a special form of [[semantic network]]<!--[[R. H. Richens links to somebody else-->.<ref>R. H. Richens: "General program for mechanical translation between any two languages via an algebraic interlingua". Cambridge Language Research Unit. ''Mechanical Translation'', November 1956; p. 37</ref> designed to represent concepts and their semantic similarity. Its main contribution is reducing the complexity of calculating semantic distances. Bendeck (2004, 2008) introduced the concept of ''semantic similarity networks'' (SSN) as the specialization of a semantic network to measure semantic similarity from ontological representations.<ref>Fawsy Bendeck, Three Fold "Ontology + Model + Instance (OMI) – Semantic Unification Process, In International Conference on Advances in Internet, Processing, System and Interdisciplinary Research (IPSI-2004), Stockholm, Sep 2004, {{ISBN|86-7466-1173}}.</ref> Implementations include genetic information handling.<ref>{{cite journal|last1=Jiang|first1=R.|last2=Gan|first2=M.|last3=He|first3=P.|year=2011|title=Constructing a gene semantic similarity network for the inference of disease genes|journal=BMC Systems Biology|volume=5|issue=2|pages=2|doi=10.1186/1752-0509-5-S2-S2|pmc=3287482|pmid=22784573 |doi-access=free }}</ref><ref>{{cite book|last1=Guzzi|first1=P. H.|title=International Workshop on New Frontiers in Mining Complex Patterns|last2=Veltri|first2=P.|last3=Cannataro|first3=M.|publisher=Springer|year=2013|location=Cham|pages=201–213|chapter=Thresholding of semantic similarity networks using a spectral graph-based technique|arxiv=1305.4858|bibcode=2013arXiv1305.4858H}}</ref>
The concept is formally defined (Bendeck 2008) as a [[directed graph]], with concepts represented as [[Vertex (graph theory)|nodes]] and semantic similarity relations as [[Graph (discrete mathematics)|edges]].<ref name=bendeck>{{cite book|last=Bendeck|first=F.|year=2008|title=WSM-P Workflow Semantic Matching Platform, PhD dissertation, University of Trier, Germany |publisher=Verlag Dr. Hut|id={{ASIN|3899638549|country=de}}}}</ref> The relationships are grouped into relation types. The concepts and relations contain attribute values to evaluate the [[semantic similarity]]<ref>P. Resnik. Using Information Content to Evaluate Semantic Similarity in a Taxonomy. Proc. the 14th International Joint Conference on Artificial Intelligence, 448–453, 1995.</ref> between concepts. The semantic similarity relationships of the SSN represent several of the general relationship types of the standard [[Semantic network]], reducing the complexity of the (normally, very large) network for calculations of semantics. SSNs define relation types as templates (and [[Taxonomy (general)|taxonomy]] of relations) for semantic similarity attributes that are common to relations of the same type. SSN representation allows propagation algorithms to faster calculate semantic similarities, including stop conditions within a specified threshold. This reduces the computation time and power required for calculation.
A more recent publications on Semantic Matching and Semantic Similarity Networks could be found in (Bendeck 2019).<ref name=bendeck2019>{{cite book|last=Bendeck|first=Fawsy |year=2019|title=Artificial Intelligence – Semantic Matching and Semantic Similarity Networks, Germany |publisher=Verlag Dr. Hut|id={{ASIN|3843940762|country=de}}}}</ref>
Specific Semantic Similarity Network application on healthcare was presented at the Healthcare information exchange Format (FHIR European Conference) 2019.<ref>[https://www.devdays.com/devdays-europe-2019/ FHIR Amsterdam]</ref><ref>Recently reference in the (2017) [http://www.gabormelli.com/RKB/Deep_Semantic_Similarity_Neural_Network_(DSSNN) Deep_Semantic_Similarity_Neural_Network_(DSSNN)]</ref>
The latest evolution in [[Artificial Intelligence]] (like [[ChatGPT]], based on [[Large language model]]), relay strongly on [[evolutionary computation]], the next level will be to include [[semantic unification]] (like in the [[Semantic Networks]] and this '''Semantic similarity network''') to extend the current models with more powerful understanding tools.
==References== {{reflist}}
[[Category:Knowledge representation]] [[Category:Semantic relations]]