{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T08:37:58Z","timestamp":1771576678988,"version":"3.50.1"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"OOPSLA2","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1908633; CCF1763674; IIS-1845900"],"award-info":[{"award-number":["CCF-1908633; CCF1763674; IIS-1845900"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA8750-19-2-0006; FA8750-19-1-0501"],"award-info":[{"award-number":["FA8750-19-2-0006; FA8750-19-1-0501"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Program. Lang."],"published-print":{"date-parts":[[2022,10,31]]},"abstract":"<jats:p>\n            We present Seq2Parse, a language-agnostic neurosymbolic approach to automatically repairing parse errors. Seq2Parse is based on the insight that\n            <jats:italic>Symbolic<\/jats:italic>\n            Error Correcting (EC) Parsers can, in principle, synthesize repairs, but, in practice, are overwhelmed by the many error-correction rules that are not\n            <jats:italic>relevant<\/jats:italic>\n            to the particular program that requires repair. In contrast,\n            <jats:italic>Neural<\/jats:italic>\n            approaches are fooled by the large space of possible sequence level edits, but can precisely pinpoint the set of EC-rules that\n            <jats:italic>are<\/jats:italic>\n            relevant to a particular program. We show how to combine their complementary strengths by using neural methods to train a sequence classifier that predicts the small set of relevant EC-rules for an ill-parsed program, after which, the symbolic EC-parsing algorithm can make short work of generating useful repairs. We train and evaluate our method on a dataset of 1,100,000 Python programs, and show that Seq2Parse is\n            <jats:italic>accurate<\/jats:italic>\n            and\n            <jats:italic>efficient<\/jats:italic>\n            : it can parse 94% of our tests within 2.1 seconds, while generating the exact user fix in 1 out 3 of the cases; and\n            <jats:italic>useful<\/jats:italic>\n            : humans perceive both Seq2Parse-generated error locations and repairs to be almost as good as human-generated ones in a statistically-significant manner.\n          <\/jats:p>","DOI":"10.1145\/3563330","type":"journal-article","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T20:23:35Z","timestamp":1667247815000},"page":"1180-1206","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Seq2Parse: neurosymbolic parse error repair"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1071-8038","authenticated-orcid":false,"given":"Georgios","family":"Sakkas","sequence":"first","affiliation":[{"name":"University of California at San Diego, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4618-4939","authenticated-orcid":false,"given":"Madeline","family":"Endres","sequence":"additional","affiliation":[{"name":"University of Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4579-5754","authenticated-orcid":false,"given":"Philip J.","family":"Guo","sequence":"additional","affiliation":[{"name":"University of California at San Diego, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6749-2204","authenticated-orcid":false,"given":"Westley","family":"Weimer","sequence":"additional","affiliation":[{"name":"University of Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1802-9421","authenticated-orcid":false,"given":"Ranjit","family":"Jhala","sequence":"additional","affiliation":[{"name":"University of California at San Diego, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3160489.3160490"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09942-y"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/356628.356629"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/0201022"},{"key":"e_1_2_1_5_1","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate. CoRR, abs\/1409.0473","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2015. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR, abs\/1409.0473 ( 2015 ). Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR, abs\/1409.0473 (2015)."},{"key":"#cr-split#-e_1_2_1_6_1.1","unstructured":"Sahil Bhatia and Rishabh Singh. 2016. Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks. https:\/\/doi.org\/10.48550\/ARXIV.1603.06129 10.48550\/ARXIV.1603.06129"},{"key":"#cr-split#-e_1_2_1_6_1.2","unstructured":"Sahil Bhatia and Rishabh Singh. 2016. Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks. https:\/\/doi.org\/10.48550\/ARXIV.1603.06129"},{"key":"e_1_2_1_7_1","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop Christopher M.","unstructured":"Christopher M. Bishop . 2006. Pattern Recognition and Machine Learning (Information Science and Statistics) . Springer-Verlag , Berlin, Heidelberg . 209\u2013210. isbn:0387310738 Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin, Heidelberg. 209\u2013210. isbn:0387310738"},{"key":"#cr-split#-e_1_2_1_8_1.1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165 10.48550\/ARXIV.2005.14165"},{"key":"#cr-split#-e_1_2_1_8_1.2","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/22719.22720"},{"key":"e_1_2_1_10_1","volume-title":"LR Parsing: Theory and Practice","author":"Chapman Nigel P","unstructured":"Nigel P Chapman . 1987. LR Parsing: Theory and Practice . Cambridge University Press , New York, NY, USA . isbn:0-521-30413-X Nigel P Chapman. 1987. LR Parsing: Theory and Practice. Cambridge University Press, New York, NY, USA. isbn:0-521-30413-X"},{"key":"e_1_2_1_11_1","unstructured":"Michael Collins. 2013. Probabilistic Context-Free Grammars (PCFGs). Lecture Notes https:\/\/u.cs.biu.ac.il\/~89-680\/collins-pcfgs.pdf \t\t\t\t  Michael Collins. 2013. Probabilistic Context-Free Grammars (PCFGs). Lecture Notes https:\/\/u.cs.biu.ac.il\/~89-680\/collins-pcfgs.pdf"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/586088.586092"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328778.3366860"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2325296.2325318"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/362007.362035"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00045"},{"key":"e_1_2_1_17_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow , Yoshua Bengio , and Aaron Courville . 2016. Deep Learning . MIT Press , 180\u2013184. http:\/\/www.deeplearningbook.org Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, 180\u2013184. http:\/\/www.deeplearningbook.org"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192387"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2445196.2445368"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10742"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99344-7_5"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76626-8_35"},{"key":"e_1_2_1_24_1","volume-title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE.","author":"Jiang Nan","year":"2021","unstructured":"Nan Jiang , Thibaud Lutellier , and Lin Tan . 2021 . CURE: Code-Aware Neural Machine Translation for Automatic Program Repair. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE. Nan Jiang, Thibaud Lutellier, and Lin Tan. 2021. CURE: Code-Aware Neural Machine Translation for Automatic Program Repair. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE."},{"key":"e_1_2_1_25_1","volume-title":"Rush","author":"Kim Yoon","year":"2017","unstructured":"Yoon Kim , Carl Denton , Luong Hoang , and Alexander M . Rush . 2017 . Structured Attention Networks. CoRR , abs\/1702.00887 (2017), arXiv:1702.00887. arxiv:1702.00887 Yoon Kim, Carl Denton, Luong Hoang, and Alexander M. Rush. 2017. Structured Attention Networks. CoRR, abs\/1702.00887 (2017), arXiv:1702.00887. arxiv:1702.00887"},{"key":"e_1_2_1_26_1","volume-title":"Adam: A Method for Stochastic Optimization. 22 Dec., arxiv:1412.6980.","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A Method for Stochastic Optimization. 22 Dec., arxiv:1412.6980. Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. 22 Dec., arxiv:1412.6980."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(65)90426-2"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2931051"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the Fifth Australasian Conference on Computing Education -","volume":"20","author":"Sarah","unstructured":"Sarah K. Kummerfeld and Judy Kay. 2003. The Neglected Battle Fields of Syntax Errors . In Proceedings of the Fifth Australasian Conference on Computing Education - Volume 20 (ACE \u201903). Australian Computer Society, Inc., AUS. 105\u2013111. isbn:0909925984 Sarah K. Kummerfeld and Judy Kay. 2003. The Neglected Battle Fields of Syntax Errors. In Proceedings of the Fifth Australasian Conference on Computing Education - Volume 20 (ACE \u201903). Australian Computer Society, Inc., AUS. 105\u2013111. isbn:0909925984"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397369"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2013.54"},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Philippe McLean and R. Nigel Horspool. 1996. A Faster Earley Parser. In CC. \t\t\t\t  Philippe McLean and R. Nigel Horspool. 1996. A Faster Earley Parser. In CC.","DOI":"10.1007\/3-540-61053-7_68"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01840433"},{"key":"e_1_2_1_34_1","volume-title":"International Conference on Machine Learning. 807\u2013814","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E Hinton . 2010 . Rectified linear units improve restricted boltzmann machines . In International Conference on Machine Learning. 807\u2013814 . Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In International Conference on Machine Learning. 807\u2013814."},{"key":"e_1_2_1_35_1","volume-title":"Neural Networks and Deep Learning","author":"Nielsen Michael A","unstructured":"Michael A Nielsen . 2015. Neural Networks and Deep Learning . Determination Press . Michael A Nielsen. 2015. Neural Networks and Deep Learning. Determination Press."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001445"},{"key":"#cr-split#-e_1_2_1_37_1.1","unstructured":"Yewen Pu Karthik Narasimhan Armando Solar-Lezama and Regina Barzilay. 2016. sk_p: a neural program corrector for MOOCs. https:\/\/doi.org\/10.48550\/ARXIV.1607.02902 10.48550\/ARXIV.1607.02902"},{"key":"#cr-split#-e_1_2_1_37_1.2","unstructured":"Yewen Pu Karthik Narasimhan Armando Solar-Lezama and Regina Barzilay. 2016. sk_p: a neural program corrector for MOOCs. https:\/\/doi.org\/10.48550\/ARXIV.1607.02902"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077618"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485535"},{"key":"#cr-split#-e_1_2_1_40_1.1","unstructured":"Sanguthevar Rajasekaran and Marius Nicolae. 2014. An error correcting parser for context free grammars that takes less than cubic time. https:\/\/doi.org\/10.48550\/ARXIV.1406.3405 10.48550\/ARXIV.1406.3405"},{"key":"#cr-split#-e_1_2_1_40_1.2","unstructured":"Sanguthevar Rajasekaran and Marius Nicolae. 2014. An error correcting parser for context free grammars that takes less than cubic time. https:\/\/doi.org\/10.48550\/ARXIV.1406.3405"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3386005"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7080357"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_2_1_45_1","volume-title":"Le","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V . Le . 2014 . Sequence to Sequence Learning with Neural Networks . arxiv:1409.3215. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. arxiv:1409.3215."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1976.5009254"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1064165.1064173"},{"key":"e_1_2_1_48_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , \u0141 ukasz Kaiser, and Illia Polosukhin . 2017 . Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). 30, Curran Associates, Inc ., 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). 30, Curran Associates, Inc., 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485477"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192384"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389252"}],"container-title":["Proceedings of the ACM on Programming Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563330","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563330","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:10Z","timestamp":1750178290000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":56,"journal-issue":{"issue":"OOPSLA2","published-print":{"date-parts":[[2022,10,31]]}},"alternative-id":["10.1145\/3563330"],"URL":"https:\/\/doi.org\/10.1145\/3563330","relation":{},"ISSN":["2475-1421"],"issn-type":[{"value":"2475-1421","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,31]]},"assertion":[{"value":"2022-10-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}