Learning to mine aligned code and natural language pairs from stack overflow
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with fine-grained alignments. Stack Overflow (SO) is a promising source to create such a data set: the questions are diverse and most of them have corresponding answers with high quality code snippets. However, existing heuristic methods (e.g., pairing the title of a post with the code in the accepted answer) are limited both in their coverage and the correctness of the NL-code pairs obtained. In this paper, we propose a novel method to mine high-quality aligned data from SO using two sets of features: hand-crafted features considering the structure of the extracted snippets, and correspondence features obtained by training a probabilistic model to capture the correlation between NL and code using neural networks. These features are fed into a classifier that determines the quality of mined NL-code pairs. Experiments using Python and Java as test beds show that the proposed method greatly expands coverage and accuracy over existing mining methods, even when using only a small number of labeled examples. Further, we find that reasonable results are achieved even when training the classifier on one language and testing on another, showing promise for scaling NL-code mining to a wide variety of programming languages beyond those for which we are able to annotate data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This model reports state-of-the-art accuracy on the CoNaLa benchmark dataset [122]”
From In-IDE Code Generation from Natural Language: Promise and Challenges (2022) · cites this paper as [122]
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.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“vent overfitting, on the input of the last softmax layer over target words (p = 0.5), and recurrent dropout [11] on RNNs (p = 0.2). We train the network using the widely used optimization method Adam [18]. To evaluate the neural network, we use the remaining 10% of pairs left aside for testing, retaining the model wit…”
MethodInfluential(2014) · Cited by 33,419
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“So how do neural MT models calculate this probability? We will explain a basic outline of a basic model called the encoder-decoder model [39], and refer readers to references for details [4, 25, 39].”
BackgroundEffective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · cited 1×
“allows the model to “focus” on particular words in the source snippet S when generating the intent I. The details of attention are beyond the scope of this paper, but interested readers can reference [4, 22]. Why attentional neural MT models?: Attention-based neural MT models are well-suited to the task of learning co…”
BackgroundLearning deep structured semantic models for web search using clickthrough data
Huang, P.-S., He, X., Gao, J., Deng, L., Acero, A., & Heck, L. (2013) · Proceedings of the 22nd ACM international conference on Information & Knowledge Management · doi:10.1145/2505515.2505665 · Cited by 2,009 · cited 1×
“Second, they are powerful models that can learn correspondences on a variety of levels; from simple phenomena such as direct word-by-word matches [12], to soft paraphrases [36], to weak correspondences between keywords and large documents for information retrieval [14].”
BackgroundInternational Conference on Learning Representations (ICLR)
Abbas, M. Z. A., Kivinen, J., & Raiko, T. (2016) · Cited by 1,694
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
Gu, J., Lu, Z., Li, H., & Li, V. O. K. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1154 · Cited by 1,446 · cited 1×
“classifier, as described in the following paragraph. Second, they are powerful models that can learn correspondences on a variety of levels; from simple phenomena such as direct word-by-word matches [12], to soft paraphrases [36], to weak correspondences between keywords and large documents for information retrieval […”
BackgroundStatistical machine translation
(2010) · Choice Reviews Online · doi:10.5860/choice.47-6293 · Cited by 1,309
Recurrent Continuous Translation Models
Kalchbrenner, N., & Blunsom, P. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1176 · Cited by 1,232 · cited 1×
“between natural language and code for the purposes of code summarization [15, 30], code synthesis from natural language [21], and code retrieval [3]. In particular, we use a model based on neural MT [4, 17], a method for MT based on neural networks that is well-suited for this task of learning correspondences for a va…”
MethodGet another label? improving data quality and data mining using multiple, noisy labelers
Sheng, V. S., Provost, F., & Ipeirotis, P. G. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401965 · Cited by 1,165 · cited 1×
“However, the statistical models that power many such applications are only as useful as the data they are trained on, i.e. , garbage in, garbage out [35].”
BackgroundA theoretically grounded application of dropout in recurrent neural networks
Gal, Y., & Ghahramani, Z. (2016) · Cambridge University Engineering Department Publications Database · Cited by 1,089
Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection
Socher, R., Huang, E., Pennin, J., Manning, C. D., & Ng, A. Y. (2011) · neural information processing systems · Cited by 958
Summarizing Source Code using a Neural Attention Model
Iyer, S., Konstas, I., Cheung, A., & Zettlemoyer, L. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1195 · Cited by 701
A Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1041 · Cited by 623
Self-citationA Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · arXiv · doi:10.48550/arxiv.1704.01696 · Cited by 585
Self-citationSuggesting accurate method and class names
Allamanis, M., Barr, E. T., Bird, C., & Sutton, C. (2015) · Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering · doi:10.1145/2786805.2786849 · Cited by 369
Building a Semantic Parser Overnight
Wang, Y., Berant, J., & Liang, P. (2015) · 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) · doi:10.3115/v1/p15-1129 · Cited by 318 · cited 1×
“de-block sized candidates, aiming to recover code solutions that exactly answer the intent. Finally, some work has asked programmers to manually write NL descriptions for code [20, 30], or vice-versa [41]. This allows for the generation of high-quality data, but is time consuming and does not scale beyond limited doma…”
BackgroundAbstract Syntax Networks for Code Generation and Semantic Parsing
Rabinovich, M., Stern, M., & Klein, D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1105 · Cited by 312 · cited 1×
“.e., garbage in, garbage out [35]. For a particular class of applications, such as source code retrieval given a NL query [42], source code summarization in NL [15], and source code synthesis from NL [33, 47], all of which involve correspondence between NL utterances and code, it is essential to have access to high vo…”
BackgroundOn the naturalness of software
Hindle, A., Barr, E. T., Gabel, M., Su, Z., & Devanbu, P. (2016) · Communications of the ACM · doi:10.1145/2902362 · Cited by 307 · cited 1×
“…researchers to expand from models of source code and natural language (NL) created using hand-crafted rules, which have a long history [23], to data-driven models that have proven flexible, relatively easy-to-create, and often more effective than corresponding hand-crafted precursors [13, 27].”
BackgroundDyNet: The Dynamic Neural Network Toolkit
Neubig, G., Dyer, C., Goldberg, Y., Matthews, A., Ammar, W., Anastasopoulos, A., Ballesteros, M., Chiang, D., Clothiaux, D., Cohn, T., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.03980 · Cited by 302 · cited 1×
“6 We implement our neural correspondencemodel using theDyNet neural network toolkit [26].”
MethodSelf-citationPredicting Program Properties from "Big Code"
Raychev, V., Vechev, M., & Krause, A. (2015) · Proceedings of the 42nd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages · doi:10.1145/2676726.2677009 · Cited by 296
Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation
Oda, Y., Fudaba, H., Neubig, G., Hata, H., Sakti, S., Toda, T., & Nakamura, S. (2015) · 2015 30th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2015.36 · Cited by 250 · cited 2×
“ore fine-grained, sub-code-block sized candidates, aiming to recover code solutions that exactly answer the intent. Finally, some work has asked programmers to manually write NL descriptions for code [20, 30], or vice-versa [41]. This allows for the generation of high-quality data, but is time consuming and does not s…”
BackgroundMethodSelf-citationAutoComment: Mining question and answer sites for automatic comment generation
Wong, E., Yang, J., & Tan, L. (2013) · 2013 28th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2013.6693113 · Cited by 245 · cited 8×
“, only consider accepted answers with a single code block or with high vote counts, or filtering out print statements in Python, much like one thrust of prior work [15, 44]); fine-tuning heuristics may achieve high pair quality, but this inherently reduces the size of the mined data set and it may also be very languag…”
BackgroundMethodResultInfluentialNeural Machine Translation and Sequence-to-sequence Models: A TutorialPreprint
Neubig, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01619 · Cited by 217 · cited 1×
“So how do neural MT models calculate this probability? We will explain a basic outline of a basic model called the encoder-decoder model [39], and refer readers to references for details [4, 25, 39].”
BackgroundSelf-citationBimodal Modelling of Source Code and Natural Language
Allamanis, M., Tarlow, D., Gordon, A. D., & Wei, Y. (2015) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 215
A study of the uniqueness of source code
Gabel, M., & Su, Z. (2010) · Proceedings of the eighteenth ACM SIGSOFT international symposium on Foundations of software engineering · doi:10.1145/1882291.1882315 · Cited by 215 · cited 1×
“First, it is highly repetitive [8, 10], therefore”
Natural language programming: Styles, strategies, and contrasts
Miller, L. A. (1981) · IBM Systems Journal · doi:10.1147/sj.202.0184 · Cited by 178 · cited 1×
“This statistical predictability enabled researchers to expand frommodels of source code and natural language (NL) created using hand-crafted rules, which have a long history [23], to data-driven models that have proven flexible, relatively easy-to-create, and often more effective than corresponding hand-crafted precur…”
BackgroundSNIFF: A Search Engine for Java Using Free-Form Queries
Chatterjee, S., Juvekar, S., & Sen, K. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-00593-0_26 · Cited by 166 · cited 2×
“, [15, 44, 46, 48]), while there has been research on mining from other data sources such as API documentation [5, 6, 24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31].”
BackgroundMethodCloCom: Mining existing source code for automatic comment generation
Wong, E., Liu, T., & Tan, L. (2015) · 2015 IEEE 22nd International Conference on Software Analysis, Evolution, and Reengineering (SANER) · doi:10.1109/saner.2015.7081848 · Cited by 162 · cited 1×
“a? Our work falls in the line of mining intent-snippet pairs from SO (e.g., [15, 44, 46, 48]), while there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31]. It is likely that…”
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
Quirk, C., Mooney, R., & Galley, M. (2015) · 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) · doi:10.3115/v1/p15-1085 · Cited by 150 · cited 2×
“line of mining intent-snippet pairs from SO (e.g., [15, 44, 46, 48]), while there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31]. It is likely that it could be adapted to w…”
BackgroundNL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
Lin, X., Wang, C., Zettlemoyer, L., & Ernst, M. D. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/42er6x4bacdf · Cited by 144
Lexical statistical machine translation for language migration
Nguyen, A. T., Nguyen, T. T., & Nguyen, T. N. (2013) · Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering · doi:10.1145/2491411.2494584 · Cited by 136 · cited 1×
“Recent years have witnessed the burgeoning of a new suite of developer assistance tools based on natural language processing (NLP) techniques, for code completion [9], source code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval…”
BackgroundA Convolutional Attention Network for Extreme Summarization of Source Code
Allamanis, M., Peng, H. M., & Sutton, C. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.03001 · Cited by 126 · cited 2×
“Recent years have witnessed the burgeoning of a new suite of developer assistance tools based on natural language processing (NLP) techniques, for code completion [9], source code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval…”
BackgroundProgram synthesis using natural language
Desai, A., Gulwani, S., Hingorani, V., Jain, N., Karkare, A., Marron, M., R, S., & Roy, S. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884786 · Cited by 111 · cited 1×
“…on natural language processing (NLP) techniques, for code completion [9], source code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval [3, 42] and even code synthesis from natural language [7, 21, 32, 47].”
BackgroundGenerating Parameter Comments and Integrating with Method Summaries
Sridhara, G., Pollock, L., & Vijay-Shanker, K. (2011) · 2011 IEEE 19th International Conference on Program Comprehension · doi:10.1109/icpc.2011.28 · Cited by 104 · cited 1×
“s from SO (e.g., [15, 44, 46, 48]), while there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31]. It is likely that it could be adapted to work with other sources, requiring…”
BackgroundNatural Language Models for Predicting Programming Comments
Movshovitz‐Attias, D., & Cohen, W. W. (2018) · Figshare · doi:10.1184/r1/6475913 · Cited by 100
Statistical learning approach for mining API usage mappings for code migration
Nguyen, A. T., Nguyen, H. A., Nguyen, T. T., & Nguyen, T. N. (2014) · Proceedings of the 29th ACM/IEEE International Conference on Automated Software Engineering · doi:10.1145/2642937.2643010 · Cited by 96 · cited 2×
“This statistical predictability enabled researchers to expand frommodels of source code and natural language (NL) created using hand-crafted rules, which have a long history [23], to data-driven models that have proven flexible, relatively easy-to-create, and often more effective than corresponding hand-crafted precur…”
BackgroundBarone, A. V. M., & Sennrich, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.02275 · Cited by 96 · cited 1×
“, [15, 44, 46, 48]), while there has been research on mining from other data sources such as API documentation [5, 6, 24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31].”
BackgroundMining source code descriptions from developer communications
Panichella, S., Aponte, J., Penta, M. D., Marcus, A., & Canfora, G. (2012) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc.2012.6240510 · Cited by 91 · cited 1×
“hile there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31]. It is likely that it could be adapted to work with other sources, requiring only changes in the definition of our…”
BackgroundLearning to rank code examples for code search engines
Niu, H., Keivanloo, I., & Zou, Y. (2016) · Empirical Software Engineering · doi:10.1007/s10664-015-9421-5 · Cited by 89 · cited 1×
“Some work on code search has been performed by retrieving candidate code snippets given an intent based on weighted keyword matches and other features [29, 42].”
MethodNeural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
Locascio, N., Narasimhan, K., DeLeon, E., Kushman, N., & Barzilay, R. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1197 · Cited by 87 · cited 3×
“code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval [3, 42] and even code synthesis from natural language [7, 21, 32, 47]. Besides the creativity and diligence of the researchers involved, these recent success stories can be a…”
BackgroundMethodFrom Query to Usable Code: An Analysis of Stack Overflow Code SnippetsPreprint
Yang, D., Hussain, A., & Lopes, C. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.04464 · Cited by 80 · cited 1×
“two programming languages: Python and Java. These languages were chosen due to their large differences in syntax and verbosity, which have been shown to effect characteristics of code snippets on SO [45]. Learning unsupervised features: We start by filtering the SO questions in the Stack Exchange data dump3 by tag (Py…”
MethodStaQC: A Systematically Mined Question-Code Dataset from Stack Overflow
Yao, Z., Weld, D. S., Chen, W.-P., & Sun, H. (2018) · Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18 · doi:10.1145/3178876.3186081 · Cited by 76 · cited 2×
“s. We can view these methods from several perspectives: Data Sources: First, what data sources do they use to mine their data? Our work falls in the line of mining intent-snippet pairs from SO (e.g., [15, 44, 46, 48]), while there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comm…”
BackgroundMethodFrom query to usable code: an analysis of stack overflow code snippets
Yang, D., Hussain, A., & Lopes, C. V. (2016) · Proceedings of the 13th International Conference on Mining Software Repositories · doi:10.1145/2901739.2901767 · Cited by 74 · cited 1×
“two programming languages: Python and Java. These languages were chosen due to their large differences in syntax and verbosity, which have been shown to effect characteristics of code snippets on SO [45]. Learning unsupervised features: We start by filtering the SO questions in the Stack Exchange data dump3 by tag (Py…”
MethodDebnath, S. (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.22721271 · Cited by 65
Recovering clear, natural identifiers from obfuscated JS names
Vasilescu, B., Casalnuovo, C., & Devanbu, P. (2017) · Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering · doi:10.1145/3106237.3106289 · Cited by 63
Self-citationMeaningful variable names for decompiled code: a machine translation approach
Jaffe, A., Lacomis, J., Schwartz, E. J., Goues, C. L., & Vasilescu, B. (2018) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1145/3196321.3196330 · Cited by 60 · cited 1×
“Recent years have witnessed the burgeoning of a new suite of developer assistance tools based on natural language processing (NLP) techniques, for code completion [9], source code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval…”
BackgroundSelf-citationExample overflow: Using social media for code recommendation
Zagalsky, A., Barzilay, O., & Yehudai, A. (2012) · Cited by 47
CACHECA: A Cache Language Model Based Code Suggestion Tool
Franks, C., Tu, Z., Dévanbu, P., & Hellendoorn, V. J. (2015) · Cited by 34
CACHECA: A Cache Language Model Based Code Suggestion Tool
Franks, C., Tu, Z., Devanbu, P., & Hellendoorn, V. (2015) · 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering · doi:10.1109/icse.2015.228 · Cited by 30
Statistical Machine Translation
Specia, L. (2014) · IGI Global eBooks · doi:10.4018/978-1-4666-6042-7.ch043 · Cited by 20
Building Bing Developer Assistant
Wei, Y., Chandrasekaran, N., Gulwani, S., & Hamadi, Y. (2019) · Cited by 14
New Initiative: The Naturalness of Software
Dévanbu, P. (2015) · Cited by 9
Research works printed but not linked: 7
- 10.5555/2819009.2819143 · doi:10.5555/2819009.2819143
- Gal Yarin, 2016, Annual Conference on Neural Information Processing Systems (NIPS). 1019--1027
- Diederik, 2014, Kingma and Jimmy Ba
- Lin Xi Victoria, 2018, International Conference on Language Resources and Evaluation (LREC)
- Luong Thang, Conference on Empirical Methods in Natural Language Processing (EMNLP). ACL, 1412--1421
- 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
- 10.5555/2666719.2666728 · doi:10.5555/2666719.2666728
Cited by
Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., et al. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1425 · Cited by 1,034
“, 2018), and CoNaLa (Yin et al., 2018).”
BackgroundCodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Lu, S., Guo, D., Ren, S., Huang, J., Svyatkovskiy, A., Blanco, A., Clement, C., Drain, D., Jiang, D., Tang, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.04664 · Cited by 536
A Neural Model for Generating Natural Language Summaries of Program Subroutines
LeClair, A., Jiang, S., & McMillan, C. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE) · doi:10.1109/icse.2019.00087 · Cited by 294
“[21], Movshovitz et al.”
A Survey on Large Language Models for Code Generation
Jiang, J., Wang, F., Shen, J., Kim, S., & Kim, S. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3747588 · Cited by 251
InCoder: A Generative Model for Code Infilling and Synthesis
Fried, D., Aghajanyan, A., Lin, J., Wang, S., Wallace, E., Shi, F., Zhong, R., Yih, W.-T., Zettlemoyer, L., & Lewis, M. (2022) · arXiv · doi:10.48550/arxiv.2204.05999 · Cited by 187
“, input-output examples [12, 28, 19, 13], partial implementations [58], or natural language descriptions [74, 73, 72, 42, 18] of the desired program as input.”
Background
Metadata
- Authors
- Yin, P., Deng, B., Chen, E., Vasilescu, B., & Neubig, G.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 15th International Conference on Mining Software Repositories
- Publisher
- ACM
- Published
- 2018-05-28
- Pages
- 476-486
- OpenAlex
- W2964315653
- Semantic Scholar
- 1a53e7446274016f737236bdd48e3ff05d966384
- Cited by
- 218
- References
- 51
- Citations by year
- 2026: 17 · 2025: 20 · 2024: 32 · 2023: 33 · 2022: 28 · 2021: 35 · 2020: 37 · 2019: 14 · 2018: 2
- FWCI
- 17.27
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Conference on Mining Software Repositories (MSR) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Keywords
- Stack Overflow, code mining, code search, code summarization, program synthesis, stochastic modeling, handcrafted features, cross-lingual generalization, programming languages
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.