Delayed interpretation, shallow processing and constructions: the basis of the "interpret whenever possible" principle

Philippe Blache (1)

1 LPL - Laboratoire Parole et Langage

We propose in this paper to investigate the "interpret whenever possible" principle which consists in delaying the processing mechanisms until enough information becomes available. This principle relies on the identification of elementary units called chunks, that are identified by means a basic features. These chunks are segments of the input to be processed. In some cases, depending on the accessibility of the information they bear, chunk can be linguistically structured elements. In other cases, they are simple segments. Chunks are stored in a buffer of the working memory and progressively grouped (on the basis of a cohesion measure) when possible, identifying progressively the different constructions of the input. The global interpretation of a linguistic input is then not based anymore on a word-byword mechanism, but on the grouping of these constructions that are constitute the backbone of the "interpret whenever possible" principle.

Domaines: Intelligence artificielle [cs.AI]; Interface homme-machine [cs.HC]; Traitement du texte et du document; Linguistique; Sciences cognitives

Philippe Blache. Delayed interpretation, shallow processing and constructions: the basis of the "interpret whenever possible" principle. Cognitive Approach to Natural Language Processing, 2017. ⟨hal-01907628⟩