Constraints First: A New MDD-based Model to Generate Sentences Under Constraints
This provides a major breakthrough for standardized sentence generation in vision screening, with potential to enhance the MNREAD test and other applications, though it is incremental in method.
The paper tackled generating strongly constrained sentences for vision screening by formalizing it as a combinatorial optimization problem using multivalued decision diagrams (MDD) and filtering with GPT-2, resulting in hundreds of candidate sentences compared to the few dozen typically available in the MNREAD test.
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.