Meaning representation: from continuity to discreteness

Fabienne Venant (1)

1 TALARIS - Natural Language Processing: representation, inference and semantics

This paper presents a geometric approach to meaning representation within the framework of continuous mathematics. Meaning representation is a central issue in Natural Language Processing, in particular for tasks like word sense disam- biguation or information extraction. We want here to discuss the relevance of using continuous models in semantics. We don't want to argue the continuous or discrete nature of lexical meaning. We use continuity as a tool to access and manipu- late lexical meaning. Following Victorri (1994), we assume that continuity or discreteness are not properties of phenomena but characterizations of theories upon phenomena. We briefly describe our theoretical framework, the dynamical construc- tion of meaning (Victorri and Fuchs, 1996), then present the way we automatically build continuous semantic spaces from a graph of synonymy and discuss their relevance and utility. We also think that discreteness and continuity can collabo- rate. We show here how we can complete our geometric representations with informations from discrete descriptions of meaning.

Domaines: Traitement du texte et du document

Fabienne Venant. Meaning representation: from continuity to discreteness. Seventh international conference on Language Resources and Evaluation (LREC), May 2010, Malte, Malta. ⟨hal-00526811⟩