Mapping Language to Code in Programmatic Context
Open accessAbstract
Source code is rarely written in isolation.It depends significantly on the programmatic context, such as the class that the code would reside in.To study this phenomenon, we introduce the task of generating class member functions given English documentation and the programmatic context provided by the rest of the class.This task is challenging because the desired code can vary greatly depending on the functionality the class provides (e.g., a sort function may or may not be available when we are asked to "return the smallest element" in a particular member variable list).We introduce CONCODE, a new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develop a new encoder-decoder architecture that models the interaction between the method documentation and the class environment.We also present a detailed error analysis suggesting that there is significant room for future work on this task.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
MCoNaLA extends CoNaLa to Spanish, Japanese, and Russian and is the only currently available benchmark for evaluating code generation from multiple natural languages.
“We note that MCoNaLA [37], which extends CoNaLa to Spanish, Japanese, and Russian, is the only currently available benchmark for evaluating code generation from multiple natural languages.”
From MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation (2023) · cites this paper as [37]
The citing sentence identifies this source as MCoNaLA, but the Introduction (p. 2) and §4 CONCODE (p. 5) identify the dataset introduced by this paper as CONCODE, built from Java projects on GitHub. Our copy does not describe an extension of CoNaLa to Spanish, Japanese, and Russian or make the claimed uniqueness assertion. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 22 · Cited by 180
Research works printed but not linked: 10
- Miltiadis Allamanis and Charles Sutton. 2014. Mining idioms from source code. In Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering , pages 472483. ACM.
- Matej Balog, Alexander L Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. 2016. Deepcoder: Learning to write programs. arXiv preprint arXiv:1611.01989 . · arXiv
- Li Dong and Mirella Lapata. 2016. Language to logical form with neural attention. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 33-43. Association for Computational Linguistics.
- Nate Kushman and Regina Barzilay. 2013. Using semantic unification to generate regular expressions from natural language. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages 826-836. Association for Computational Linguistics.
- Mehdi Hafezi Manshadi, Daniel Gildea, and James F Allen. 2013. Integrating programming by example and natural language programming. In AAAI .
- Chris Quirk, Raymond Mooney, and Michel Galley. 2015. Language to code: Learning semantic parsers for if-this-then-that recipes. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) , pages 878-888, Beijing, China. Association for Computational Linguistics.
- Maxim Rabinovich, Mitchell Stern, and Dan Klein. 2017. Abstract syntax networks for code generation and semantic parsing. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 11391149, Vancouver, Canada. Association for Computational Linguistics.
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 17151725, Berlin, Germany. Association for Computational Linguistics.
- Pengcheng Yin and Graham Neubig. 2017. A syntactic neural model for general-purpose code generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 440-450, Vancouver, Canada. Association for Computational Linguistics.
- Luke S. Zettlemoyer and Michael Collins. 2005. Learning to map sentences to logical form: structured classification with probabilistic categorial grammars. In UAI '05, Proceedings of the 21st Conference in Uncertainty in Artificial Intelligence .
- Authors
- Iyer, S., Konstas, I., Cheung, A., & Zettlemoyer, L.
- Affiliations
- University of Washington (US)
- Heriot-Watt University (GB)
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 1643-1652
- OpenAlex
- W2888925928
- Cited by
- 180
- References
- 22
- Citations by year
- 2026: 11 · 2025: 20 · 2024: 26 · 2023: 43 · 2022: 19 · 2021: 21 · 2020: 18 · 2019: 20 · 2018: 2
- FWCI
- 11.97
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1651489, 1739419, 1546083, 1252835, 1562364)
- U.S. Department of Energy (DESC0016260, FA8750-16-2-0032)
- Defense Advanced Research Projects Agency (FA8750-16-2-0032, FA8750)
- Army Research Office (W911NF-16-1-, W911NF)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- Java classes, encoder-decoder architecture, error analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
