Modelling the Semantics of Adjectives in the Ontology-Lexicon Interface

The modelling of the semantics of adjectives is notoriously challenging. We consider this problem in the context of the so called ontology-lexicon interface, which attempts to capture the semantics of words by reference to an ontology in description logics or some other, typically first-order, logical formalism. The use of first order logic (hence also description logics), while effective for nouns and verbs, breaks down in the case of adjectives. We argue that this is primarily due to a lack of logical expressivity in the underlying ontology languages. In particular, beyond the straightforward intersective adjectives, there exist gradable adjectives, requiring fuzzy or non-monotonic semantics, as well as operator adjectives, requiring second-order logic for modelling. We consider how we can extend the ontology-lexicon interface as realized by extant models such as lemon in the face of the issues mentioned above, in particular those arising in the context of modelling the ontological semantics of adjectives. We show howmore complex logical formalisms that are required to capture the ontological semantics of adjectives can be backward engineered into OWL-based modelling by means of pseudo-classes. We discuss the implications of this modelling in the context of application to ontology-based question answering.