The Computational Learning of Construction Grammars: State of the Art and Prospective Roadmap

TL;DR

The paper tackles the problem of learning large-scale, usage-based construction grammars computationally. It surveys 31 models across four learning tasks, defines 14 criteria for comparison, and proposes a roadmap to integrate diverse approaches toward scalable, language-independent learning. A key contribution is the synthesis of methods (from MDL-based segmentation to situation-grounded and cross-situational learning) and the identification of gaps preventing fully bidirectional, practical grammars. The work aims to guide future research and inform language technologies that can learn and adapt language use from rich, real-world interactions.

Abstract

This paper documents and reviews the state of the art concerning computational models of construction grammar learning. It brings together prior work on the computational learning of form-meaning pairings, which has so far been studied in several distinct areas of research. The goal of this paper is threefold. First of all, it aims to synthesise the variety of methodologies that have been proposed to date and the results that have been obtained. Second, it aims to identify those parts of the challenge that have been successfully tackled and reveal those that require further research. Finally, it aims to provide a roadmap which can help to boost and streamline future research efforts on the computational learning of large-scale, usage-based construction grammars.