PDF] Reconciling fine-grained lexical knowledge and coarse-grained ontologies in the representation of near-synonyms

A new model for representing fine-grained lexical knowledge whose basis is the idea of granularity of representation is discussed. A machine translation system must be able to adequately cope with near-synonymy for there are often many slightly different translations available for any given source language word that can each significantly and differently affect the meaning or style of a translated text. Conventional models of lexical knowledge used in natural-language processing systems are inadequate for representing near-synonyms, because they are unable to represent fine-grained lexical knowledge. We will discuss a new model for representing fine-grained lexical knowledge whose basis is the idea of granularity of representation.

A generic metamodel for data extraction and generic ontology population - Yohann Chasseray, Anne-Marie Barthe-Delanoë, Stéphane Négny, Jean-Marc Le Lann, 2022

Creating an ignorance-base: Exploring known unknowns in the scientific literature - ScienceDirect

Decoding the information structure underlying the neural representation of concepts

PDF] Near-synonymy and the structure of lexical knowledge

Decoding the information structure underlying the neural representation of concepts

Data and Knowledge Evolution

James Malone's Blog

Ontologies and the Semantic Web

Decoding the information structure underlying the neural representation of concepts