Content area

Abstract

Formal grammars are the canonical means of describing a space of programs. The finite set of rules describing the space can also be used for sampling programs within this space. One can formulate this system as a reinforcement learning problem where one represents non-terminals as states and production rules as actions. The problem then becomes how to represent a partially completed program in an effective manner for such a model working to build programs. This thesis looks into sampling programs from various domain specific languages and constructing continuous embeddings of such programs to serve in downstream machine learning tasks, including for program expansion. Qualitative and quantitative analysis of doc2vec-based embeddings is done along with development of a quantitative metric for analyzing how effectively embeddings retain the structure of partial and complete programs, with comparisons to other text-based embedding systems.

Details

1010268
Business indexing term
Title
Exploring Latent Program Spaces for Program Synthesis
Number of pages
114
Publication year
2025
Degree date
2025
School code
2409
Source
MAI 87/7(E), Masters Abstracts International
ISBN
9798270266837
Committee member
Fagg, Andrew H.; Cao, Jie
University/institution
University of Oklahoma – Graduate College
Department
Computer Science: Engineering
University location
United States -- Oklahoma, US
Degree
M.S.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
32399614
ProQuest document ID
3290558117
Document URL
https://www.proquest.com/dissertations-theses/exploring-latent-program-spaces-synthesis/docview/3290558117/se-2?accountid=208611
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Database
ProQuest One Academic