Dire n'est pas concevoir

TL;DR

This paper discusses the challenges of extracting ontologies from text, highlighting issues like corpus dependence, mismatch with expert ontologies, and linguistic limitations affecting conceptual understanding.

Contribution

It clarifies the distinction between textual knowledge and ontologies, emphasizing the limitations of current text-based conceptual modeling.

Findings

Textual conceptualizations are corpus-dependent and not true ontologies.

Ontology extraction from text often mismatches expert-defined ontologies.

Linguistic features like ellipsis affect the perception of conceptual content.

Abstract

The conceptual modelling built from text is rarely an ontology. As a matter of fact, such a conceptualization is corpus-dependent and does not offer the main properties we expect from ontology. Furthermore, ontology extracted from text in general does not match ontology defined by expert using a formal language. It is not surprising since ontology is an extra-linguistic conceptualization whereas knowledge extracted from text is the concern of textual linguistics. Incompleteness of text and using rhetorical figures, like ellipsis, modify the perception of the conceptualization we may have. Ontological knowledge, which is necessary for text understanding, is not in general embedded into documents.