Constraints First: A New MDD-based Model to Generate Sentences Under Constraints - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Constraints First: A New MDD-based Model to Generate Sentences Under Constraints

Abstract

This paper introduces a new approach to generating strongly constrained texts. We consider standardized sentence generation for the typical application of vision screening. To solve this problem, we formalize it as a discrete combinatorial optimization problem and utilize multivalued decision diagrams (MDD), a well-known data structure to deal with constraints. In our context, one key strength of MDD is to compute an exhaustive set of solutions without performing any search. Once the sentences are obtained, we apply a language model (GPT-2) to keep the best ones. We detail this for English and also for French where the agreement and conjugation rules are known to be more complex. Finally, with the help of GPT-2, we get hundreds of bona-fide candidate sentences. When compared with the few dozen sentences usually available in the well-known vision screening test (MNREAD), this brings a major breakthrough in the field of standardized sentence generation. Also, as it can be easily adapted for other languages, it has the potential to make the MNREAD test even more valuable and usable. More generally, this paper highlights MDD as a convincing alternative for constrained text generation, especially when the constraints are hard to satisfy, but also for many other prospects.
Fichier principal
Vignette du fichier
IJCAI2023.pdf (382.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04216267 , version 1 (24-09-2023)

Licence

Attribution

Identifiers

Cite

Alexandre Bonlarron, Aurelie Calabrese, Pierre Kornprobst, Jean-Charles Régin. Constraints First: A New MDD-based Model to Generate Sentences Under Constraints. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI23 ), Aug 2023, Macao SAR, China. pp.1893-1901, ⟨10.24963/ijcai.2023/210⟩. ⟨hal-04216267⟩
167 View
27 Download

Altmetric

Share

Gmail Facebook X LinkedIn More