Projects per year
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 paper, we introduce a neural methodology for learning heuristics that substantially optimise the search processes involved in constructional language processing. We validate the methodology in a case study for the CLEVR benchmark dataset. We show 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 reported in this paper 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.
|Journal||Journal of Language Modelling|
|Publication status||Accepted/In press - 2023|
- neural heuristics
- Fluid Construction Grammar
- construction grammar
- language processing
- 3 Active
EU629: Meaning and Understanding in Human-centric AI
Beuls, K., Nowe, A. & Van Eecke, P.
1/10/20 → 30/09/24
FWOTM1034: Learning Construction Grammars from Semantically Annotated Corpora or Situated Communicative Interactions
Van Eecke, P., Nowe, A. & Beuls, K.
1/10/20 → 30/09/23