The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
On the localness of software
Abstract
The n-gram language model, which has its roots in statistical natural language processing, has been shown to successfully capture the repetitive and predictable regularities (“naturalness") of source code, and help with tasks such as code suggestion, porting, and designing assistive coding devices. However, we show in this paper that this natural-language-based model fails to exploit a special property of source code: localness. We find that human-written programs are localized: they have useful local regularities that can be captured and exploited. We introduce a novel cache language model that consists of both an n-gram and an added “cache" component to exploit localness. We show empirically that the additional cache component greatly improves the n-gram approach by capturing the localness of software, as measured by both cross-entropy and suggestion accuracy. Our model’s suggestion accuracy is actually comparable to a state-of-the-art, semantically augmented language model; but it is simpler and easier to implement. Our cache language model requires nothing beyond lexicalization, and thus is applicable to all programming languages.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Vocabularies of a project are highly local, and functions from the same projects are likely to share same set of identifiers [10,22].”
From Few-shot training LLMs for project-specific code-summarization (2022) · cites this paper as [22]
In the citing paper
“It's been well-known right from the outset that language modeling for code has to deal with project-specific phenomena [10,11,22].”
From Few-shot training LLMs for project-specific code-summarization (2022) · cites this paper as [22]
Citations
Cites
(1992) · doi:10.5555/176313.176316 · Cited by 2,892
A statistical approach to machine translation
Brown, P. F., Cocke, J., Pietra, S. A. D., Pietra, V. J. D., Jelinek, F., Lafferty, J., Mercer, R. L., & Roossin, P. S. (1990) · doi:10.5555/92858.92860 · Cited by 1,655
Estimation of probabilities from sparse data for the language model component of a speech recognizer
Katz, S. (1987) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1987.1165125 · Cited by 1,637
A Maximum Likelihood Approach to Continuous Speech Recognition
Bahl, L. R., Jelinek, F., & Mercer, R. L. (1983) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1983.4767370 · Cited by 1,212
On the naturalness of software
Hindle, A., Barr, E. T., Su, Z., Gabel, M., & Dévanbu, P. (2012) · doi:10.5555/2337223.2337322 · Cited by 541
Self-citationTowards automatically generating summary comments for Java methods
Sridhara, G., Hill, E., Muppaneni, D., Pollock, L., & Vijay-Shanker, K. (2010) · Proceedings of the IEEE/ACM international conference on Automated software engineering · doi:10.1145/1858996.1859006 · Cited by 514
Semantic clustering: Identifying topics in source code
Kuhn, A., Ducasse, S., & Gîrba, T. (2007) · Information and Software Technology · doi:10.1016/j.infsof.2006.10.017 · Cited by 496
A cache-based natural language model for speech recognition
Kuhn, R., & De Mori, R. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.56193 · Cited by 495
Using task context to improve programmer productivity
Kersten, M., & Murphy, G. C. (2006) · Proceedings of the 14th ACM SIGSOFT international symposium on Foundations of software engineering · doi:10.1145/1181775.1181777 · Cited by 452
Dixon, W. J., & Mood, A. M. (1946) · Journal of the American Statistical Association · doi:10.1080/01621459.1946.10501898 · Cited by 422
Research works printed but not linked: 4
- 10.5555/2487085.2487127 · doi:10.5555/2487085.2487127
- M. Broy , F. Deißenböck , and M. Pizka . A holistic approach to software quality at work. In 3WCSQ , 2005 . M. Broy, F. Deißenböck, and M. Pizka. A holistic approach to software quality at work. In 3WCSQ, 2005.
- K. Knight . Bayesian inference with tears . Tutorial Workbook , 2009 . K. Knight. Bayesian inference with tears. Tutorial Workbook, 2009.
- 10.1145/1062455.1062526 · doi:10.1145/1062455.1062526 · Paper page
Cited by
Automatically learning semantic features for defect prediction
Wang, S., Liu, T., & Tan, L. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884804 · Cited by 689
Deep learning code fragments for code clone detection
White, M., Tufano, M., Vendome, C., & Poshyvanyk, D. (2016) · Proceedings of the 31st IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/2970276.2970326 · Cited by 558
“They are also limited by the amount of context they consider [75], yet the novel approach of casting applications in terms of “naturalness” in SE contexts has spawned many applications of this technology to new problems.”
BackgroundGu, X., Zhang, H., Zhang, D., & Kim, S. (2016) · Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering · doi:10.1145/2950290.2950334 · Cited by 485
“Statistical language models have been adapted to many software engineering tasks [26] such as learning natural code conventions [5], code suggestion [44], and code completion [37].”
MethodA Convolutional Attention Network for Extreme Summarization of Source CodePreprint
Allamanis, M., Peng, H. M., & Sutton, C. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.03001 · Cited by 624
“Research has mostly focused on tokenlevel (Nguyen et al., 2013; Tu et al., 2014) and syntax-level (Maddison & Tarlow, 2014) language models of code and translation between programming languages (Karaivanov”
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
“However, we note that these are very early efforts in this area, and new software language models 35, 49 and estimation techniques have improved on the results presented below.”
BackgroundSelf-citation
Metadata
- Authors
- Tu, Z., Su, Z., & Devanbu, P.
- Affiliations
- University of California, Davis (US)
- University of California at Davis, USA
- Venue
- Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering
- Publisher
- ACM
- Published
- 2014-11-11
- Pages
- 269-280
- OpenAlex
- W2165747537
- Cited by
- 238
- References
- 52
- Citations by year
- 2026: 4 · 2025: 14 · 2024: 16 · 2023: 21 · 2022: 16 · 2021: 27 · 2020: 33 · 2019: 29 · 2018: 26 · 2017: 9 · 2016: 23 · 2015: 20
- FWCI
- 14.79
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) (publishedVersion)
- Funders
- National Science Foundation
- 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
- n-gram language models, source code, localness, code completion, lexicalization, cross-entropy
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: On the localness of software. https://app.cochat.ai/papers/10.1145/2635868.2635875
- The paper
- Tu, Z., Su, Z., & Devanbu, P. (2014). On the localness of software. Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering. https://doi.org/10.1145/2635868.2635875
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.