Before joining USF, he worked as visiting professor at the ESSI polytechnic and EIVL engineering schools (France) then as postdoctoral researcher at the University of Fribourg's Computer Science department (Switzerland). Dr. Gaspar is an ACM SIGCSE, SIGITE and SIGEVO member and regularly serves as reviewer for international journals & conferences and as panelist for various NSF programs. His research interests include Evolutionary Algorithms, Computing Education Research, and applications to Computer-Assisted Teaching & Learning. His technology interests include Linux System Administration, Programming, Web App Development, and open source technologies in general.
Even more so than natural language, code is extremely sensitive to syntax; a small error could make an entire snippet invalid. It is therefore important to explore methods for ensuring syntactic correctness in generated code. Existing methods to resolve this issue often rely on the complex architecture of syntax-guided decoders. In this work, we present the grammar enforcement method, which introduces a separate layer that constrains the decisions of the transformer during fine-tuning according to syntactic constructs present both in the target language grammar and the given training set. We experiment with the Hearthstone dataset to study its effects on result programs and compare it with the existing state-of-art syntax-guided decoders. We demonstrate a statistically significant positive effect of grammar enforcement on the quality of generated programs in terms of exact match accuracy and grammatically correct percent of samples. At the same time, we observe lower values for text-based metrics, chrF, and BLEU, potentially indicating their inability to represent the quality of generated abstract syntax sequences.
Before joining USF, he worked as visiting professor at the ESSI polytechnic and EIVL engineering schools (France) then as postdoctoral researcher at the University of Fribourg's Computer Science department (Switzerland). Dr. Gaspar is an ACM SIGCSE, SIGITE and SIGEVO member and regularly serves as reviewer for international journals & conferences and as panelist for various NSF programs. His research interests include Evolutionary Algorithms, Computing Education Research, and applications to Computer-Assisted Teaching & Learning. His technology interests include Linux System Administration, Programming, Web App Development, and open source technologies in general.
The effect of semantically neutral tree rewrites is analyzed in the context of genetic programming applied to Boolean domain problems. Different setups of the proposed Neutral Rewrite Operator are studied from the perspective of improving performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.