Skip to main content

Modelling Lexical Semantics in Ancient Languages

Ancient Language WordNet Consortium

The Ancient Language WordNet Consortium is an international group of researchers developing electronic lexico-semantic databases for Sanskrit, Ancient Greek, Latin and Old English, under the direction of William Michael Short. These massively interlinked and interoperable ‘WordNets’ are intended to model the semantic systems of ancient languages as fully and accurately as possible, in a form that is machine-interpretable and machine-actionable, as well as cross-linguistically comparable, and thus suitable to computational ‘natural language understanding’ applications of different kinds.

The projects build on, and extend, the WordNet framework developed as part of the Fondazione Bruno Kessler's MultiWordNet project, which itself derives from the Princeton WordNet for English. In collaboration with the University of Genoa, the WordNet framework is, in particular, being extended to capture rich information about the figurative usage of words, as well as to represent large-scale metaphorical patterns that structure meaning throughout ancient languages.


Latin WordNet 

Ancient Greek WordNet 

Sanskrit WordNet


Cylleneus is a next-generation search tool for electronic corpora of ancient languages, which, by taking advantage of the WordNet databases, supports semantic querying – allowing users, in other words, to search ancient texts on the basis of their meanings. 


Cylleneus: Next-gen corpus search for electronic corpora of ancient languages

More information

If you have any queries, please contact Dr William Short.