Generative Code Modeling with Graphs

Generative Code Modeling with Graphs

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brockschmidt, Marc, Allamanis, Miltiadis, Gaunt, Alexander L, Polozov, Oleksandr
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Learning
Computer Science - Programming Languages
Statistics - Machine Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Brockschmidt, Marc
Allamanis, Miltiadis
Gaunt, Alexander L
Polozov, Oleksandr
description Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.
doi_str_mv 10.48550/arxiv.1805.08490
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1805_08490</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1805_08490</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-65ba16b0f9ba6aa6ba02b029b04481f6a5a437dc323b5e314cd01a876219c6053</originalsourceid><addsrcrecordid>eNotzr0OgjAUhuEuDga9ACcZXMFT-kMZDVE0wbiwk1Mo0gTRVOPP3avo8r3bl4eQGYWQKyFgie5p7yFVIEJQPIExWWSmNw5v9m789Fwbf_-ZzvZH_2FvrZ85vLTXCRk12F3N9F-PFJt1kW6D_JDt0lUeoIwhkEIjlRqaRKNElBoh0hAlGjhXtJEokLO4rljEtDCM8qoGiiqWEU0qCYJ5ZP67HZjlxdkTulf55ZYDl70Bg2I4qA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Generative Code Modeling with Graphs</title><source>arXiv.org</source><creator>Brockschmidt, Marc ; Allamanis, Miltiadis ; Gaunt, Alexander L ; Polozov, Oleksandr</creator><creatorcontrib>Brockschmidt, Marc ; Allamanis, Miltiadis ; Gaunt, Alexander L ; Polozov, Oleksandr</creatorcontrib><description>Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.</description><identifier>DOI: 10.48550/arxiv.1805.08490</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Programming Languages ; Statistics - Machine Learning</subject><creationdate>2018-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1805.08490$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1805.08490$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Brockschmidt, Marc</creatorcontrib><creatorcontrib>Allamanis, Miltiadis</creatorcontrib><creatorcontrib>Gaunt, Alexander L</creatorcontrib><creatorcontrib>Polozov, Oleksandr</creatorcontrib><title>Generative Code Modeling with Graphs</title><description>Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Programming Languages</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr0OgjAUhuEuDga9ACcZXMFT-kMZDVE0wbiwk1Mo0gTRVOPP3avo8r3bl4eQGYWQKyFgie5p7yFVIEJQPIExWWSmNw5v9m789Fwbf_-ZzvZH_2FvrZ85vLTXCRk12F3N9F-PFJt1kW6D_JDt0lUeoIwhkEIjlRqaRKNElBoh0hAlGjhXtJEokLO4rljEtDCM8qoGiiqWEU0qCYJ5ZP67HZjlxdkTulf55ZYDl70Bg2I4qA</recordid><startdate>20180522</startdate><enddate>20180522</enddate><creator>Brockschmidt, Marc</creator><creator>Allamanis, Miltiadis</creator><creator>Gaunt, Alexander L</creator><creator>Polozov, Oleksandr</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20180522</creationdate><title>Generative Code Modeling with Graphs</title><author>Brockschmidt, Marc ; Allamanis, Miltiadis ; Gaunt, Alexander L ; Polozov, Oleksandr</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-65ba16b0f9ba6aa6ba02b029b04481f6a5a437dc323b5e314cd01a876219c6053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Programming Languages</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Brockschmidt, Marc</creatorcontrib><creatorcontrib>Allamanis, Miltiadis</creatorcontrib><creatorcontrib>Gaunt, Alexander L</creatorcontrib><creatorcontrib>Polozov, Oleksandr</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Brockschmidt, Marc</au><au>Allamanis, Miltiadis</au><au>Gaunt, Alexander L</au><au>Polozov, Oleksandr</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Generative Code Modeling with Graphs</atitle><date>2018-05-22</date><risdate>2018</risdate><abstract>Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.</abstract><doi>10.48550/arxiv.1805.08490</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1805.08490
ispartof
issn
language eng
recordid cdi_arxiv_primary_1805_08490
source arXiv.org
subjects Computer Science - Learning
Computer Science - Programming Languages
Statistics - Machine Learning
title Generative Code Modeling with Graphs
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T00%3A46%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Generative%20Code%20Modeling%20with%20Graphs&rft.au=Brockschmidt,%20Marc&rft.date=2018-05-22&rft_id=info:doi/10.48550/arxiv.1805.08490&rft_dat=%3Carxiv_GOX%3E1805_08490%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true