Composing or Not Composing? Towards Distributional Construction Grammars

TL;DR

This paper addresses how natural language meaning is accessed when both compositional processing and pattern-based recognition operate in parallel. It proposes Distributional Construction Grammars (DCxG), which integrates Construction Grammar with distributional semantics and an activation-based recognition mechanism. The framework introduces three object types—constructions, frames, and events—to capture form/meaning pairings, world knowledge, and usage-based meaning, and it outlines how activation and similarity guide construction recognition. The work aims to provide theoretical foundations to guide experimental cognitive modeling and bridge formal and usage-based accounts of language comprehension.

Abstract

The mechanisms of comprehension during language processing remains an open question. Classically, building the meaning of a linguistic utterance is said to be incremental, step-by-step, based on a compositional process. However, many different works have shown for a long time that non-compositional phenomena are also at work. It is therefore necessary to propose a framework bringing together both approaches. We present in this paper an approach based on Construction Grammars and completing this framework in order to account for these different mechanisms. We propose first a formal definition of this framework by completing the feature structure representation proposed in Sign-Based Construction Grammars. In a second step, we present a general representation of the meaning based on the interaction of constructions, frames and events. This framework opens the door to a processing mechanism for building the meaning based on the notion of activation evaluated in terms of similarity and unification. This new approach integrates features from distributional semantics into the constructionist framework, leading to what we call Distributional Construction Grammars.