Sangam: A Confluence of Knowledge Streams

Synthesizing Object Models from Natural Language Specifications

Show simple item record

dc.contributor Solar-Lezama, Armando
dc.contributor Andreas, Jacob
dc.contributor Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.creator Gu, Alex
dc.date 2022-08-29T16:14:32Z
dc.date 2022-08-29T16:14:32Z
dc.date 2022-05
dc.date 2022-05-27T16:19:16.985Z
dc.date.accessioned 2023-02-17T19:52:44Z
dc.date.available 2023-02-17T19:52:44Z
dc.identifier https://hdl.handle.net/1721.1/144829
dc.identifier.uri http://localhost:8080/xmlui/handle/CUHPOERS/242038
dc.description Program synthesis has traditionally excelled in tasks with precise specifications such as input-output examples and formal constraints by using structured and algorithmic approaches based on enumerative search and type inference. However, traditional synthesis techniques have no mechanism of incorporating real-world knowledge, which is commonplace in software engineering. Motivated by this, we introduce a new synthesis task known as specification reification: synthesizing concrete realizations of vague, high-level application specifications. We focus on a specific instance of this: generating object models from natural language application descriptions. Towards this goal, we present three approaches for object model synthesis that leverage domain knowledge from the GPT-3 language model. In addition, we design a scoring metric to evaluate the success of synthesized object models on seven sample tasks such as classroom management and pet store applications. We demonstrate that our language-model-based synthesizers generate object models that are comparable in quality to human-generated ones.
dc.description M.Eng.
dc.format application/pdf
dc.publisher Massachusetts Institute of Technology
dc.rights In Copyright - Educational Use Permitted
dc.rights Copyright MIT
dc.rights http://rightsstatements.org/page/InC-EDU/1.0/
dc.title Synthesizing Object Models from Natural Language Specifications
dc.type Thesis


Files in this item

Files Size Format View
Gu-gua-meng-eecs-2022-thesis.pdf 486.9Kb application/pdf View/Open

This item appears in the following Collection(s)

  • DSpace@MIT [2699]
    DSpace@MIT is a digital repository for MIT's research, including peer-reviewed articles, technical reports, working papers, theses, and more.

Show simple item record

Search DSpace


Advanced Search

Browse