Constructionist approaches to language make use of form-meaning pairings, called constructions, to capture all linguistic knowledge that is necessary for comprehending and producing natural language expressions. Language processing consists then in combining the constructions of a grammar in such a way that they solve a given language comprehension or production problem. Finding such an adequate sequence of constructions constitutes a search problem that is combinatorial in nature and becomes intractable as grammars increase in size. In this micro project, we explore a neural methodology for learning heuristics that substantially optimises the search processes involved in constructional language processing.
We have validated the methodology in a case study for the CLEVR benchmark dataset. We have already shown that our novel methodology outperforms state-of-the-art techniques in terms of size of the search space and time of computation, most markedly in the production direction. The results already obtained constitute a crucial contribution towards the development of scalable constructional language processing systems, thereby overcoming the major efficiency obstacle that hinders current efforts in learning large-scale construction grammars.
Van Eecke, P., Nevens, J., & Beuls, K. (Submitted). Neural Heuristics for Scaling Constructional Language Processing.
Paul Van Eecke, Jens Nevens and Katrien Beuls (VUB-EHAI)