View in EDS

Neuro-Symbolic Program Synthesis for Data-Efficient Learning

Saved in:
Bibliographic Details
Title: Neuro-Symbolic Program Synthesis for Data-Efficient Learning
Language: English
Authors: Shraddha Govind Barke
Source: ProQuest LLC. 2024Ph.D. Dissertation, University of California, San Diego.
Availability: ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Peer Reviewed: N
Page Count: 203
Publication Date: 2024
Document Type: Dissertations/Theses - Doctoral Dissertations
Descriptors: Artificial Intelligence, Symbolic Learning, Programming, Programming Languages, Natural Language Processing, Data Processing, Computers
ISBN: 979-83-468-0714-8
Abstract: The dream of intelligent assistants to enhance programmer productivity has now become a concrete reality, with rapid advances in artificial intelligence. Large language models (LLMs) have demonstrated impressive capabilities in various domains based on the vast amount of data used to train them. However, tasks which require structured reasoning or those underrepresented in their training data continue to be a challenge for LLMs. Program synthesis offers an alternative approach to learning, particularly effective in data-efficient domains with limited training data. It focuses on searching for a program in a domain-specific language that satisfies a given user intent. Program synthesis enables learning of interpretable models that provide correctness and generalizability guarantees from a few data points leading to data-efficient learning. However, purely symbolic methods based on combinatorial search scale poorly to complex problems. To address these challenges, a hybrid paradigm called neurosymbolic synthesis is being explored. This approach integrates the best of both worlds by combining neural networks with symbolic reasoning, thereby enhancing the robustness of AI assistants. This dissertation includes technical contributions spanning symbolic, neurosymbolic and neural approaches to program synthesis. It explores the application of "symbolic" constraint-based synthesis in SYPHON to model human language, "hybrid" techniques in PROBE and HYSYNTH that guide symbolic search with a probabilistic model, and "neural" LLM-driven code generation to automate spreadsheet tasks for end users. Additionally, it focuses on strategies to improve user experience by developing more intuitive and user-friendly programming assistants for the future. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]
Abstractor: As Provided
Entry Date: 2025
Access URL: https://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:31297918
Accession Number: ED664468
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: ED664468
AccessLevel: 3
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Neuro-Symbolic Program Synthesis for Data-Efficient Learning
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Shraddha+Govind+Barke%22">Shraddha Govind Barke</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22ProQuest+LLC%22"><i>ProQuest LLC</i></searchLink>. 2024Ph.D. Dissertation, University of California, San Diego.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: N
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 203
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2024
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Dissertations/Theses - Doctoral Dissertations
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Symbolic+Learning%22">Symbolic Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Programming%22">Programming</searchLink><br /><searchLink fieldCode="DE" term="%22Programming+Languages%22">Programming Languages</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Language+Processing%22">Natural Language Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Data+Processing%22">Data Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Computers%22">Computers</searchLink>
– Name: ISBN
  Label: ISBN
  Group: ISBN
  Data: 979-83-468-0714-8
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The dream of intelligent assistants to enhance programmer productivity has now become a concrete reality, with rapid advances in artificial intelligence. Large language models (LLMs) have demonstrated impressive capabilities in various domains based on the vast amount of data used to train them. However, tasks which require structured reasoning or those underrepresented in their training data continue to be a challenge for LLMs. Program synthesis offers an alternative approach to learning, particularly effective in data-efficient domains with limited training data. It focuses on searching for a program in a domain-specific language that satisfies a given user intent. Program synthesis enables learning of interpretable models that provide correctness and generalizability guarantees from a few data points leading to data-efficient learning. However, purely symbolic methods based on combinatorial search scale poorly to complex problems. To address these challenges, a hybrid paradigm called neurosymbolic synthesis is being explored. This approach integrates the best of both worlds by combining neural networks with symbolic reasoning, thereby enhancing the robustness of AI assistants. This dissertation includes technical contributions spanning symbolic, neurosymbolic and neural approaches to program synthesis. It explores the application of "symbolic" constraint-based synthesis in SYPHON to model human language, "hybrid" techniques in PROBE and HYSYNTH that guide symbolic search with a probabilistic model, and "neural" LLM-driven code generation to automate spreadsheet tasks for end users. Additionally, it focuses on strategies to improve user experience by developing more intuitive and user-friendly programming assistants for the future. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2025
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:31297918" linkWindow="_blank">https://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:31297918</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED664468
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED664468
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 203
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Symbolic Learning
        Type: general
      – SubjectFull: Programming
        Type: general
      – SubjectFull: Programming Languages
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Data Processing
        Type: general
      – SubjectFull: Computers
        Type: general
    Titles:
      – TitleFull: Neuro-Symbolic Program Synthesis for Data-Efficient Learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Shraddha Govind Barke
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2024
          Identifiers:
            – Type: isbn-print
              Value: 979-83-468-0714-8
          Titles:
            – TitleFull: ProQuest LLC
              Type: main
ResultId 1