Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 207

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

On Learning Meaningful Code Changes Via Neural Machine Translation

Tufano, Michele, Pantiuchina, Jevgenija, Watson, Cody, Bavota, Gabriele, Poshyvanyk, Denys·2019·2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)
DOI 10.1109/icse.2019.00021
Open this paper in CoChat — free account

Abstract

Recent years have seen the rise of Deep Learning (DL) techniques applied to source code. Researchers have exploited DL to automate several development and maintenance tasks, such as writing commit messages, generating comments and detecting vulnerabilities among others. One of the long lasting dreams of applying DL to source code is the possibility to automate non-trivial coding activities. While some steps in this direction have been taken (e.g., learning how to fix bugs), there is still a glaring lack of empirical evidence on the types of code changes that can be learned and automatically applied by DL. Our goal is to make this first important step by quantitatively and qualitatively investigating the ability of a Neural Machine Translation (NMT) model to learn how to automatically apply code changes implemented by developers during pull requests. We train and experiment with the NMT model on a set of 236k pairs of code components before and after the implementation of the changes provided in the pull requests. We show that, when applied in a narrow enough context (i.e., small/medium-sized pairs of methods before/after the pull request changes), NMT can automatically replicate the changes implemented by developers during pull requests in up to 36% of the cases. Moreover, our qualitative analysis shows that the model is capable of learning and replicating a wide variety of meaningful code changes, especially refactorings and bug-fixing activities. Our results pave the way for novel research in the area of DL on code, such as the automatic learning and applications of refactoring.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icse.2019.00021

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 6 references

Research works printed but not linked: 63

  1. 10.1109/ASE.2017.8115618 · DOI · Paper page
  2. 10.1145/2642937.2642982 · DOI · Paper page
  3. 10.18653/v1/D17-1151 · DOI · Paper page
  4. berkman, 2018, Machine learning vs deep learning
  5. bahdanau, 2014, Neural machine translation by jointly learning to align and translate, CoRR, abs 1409 473
  6. 10.1109/ICSME.2017.69 · DOI
  7. 10.1145/2950290.2983985 · DOI
  8. 10.1109/ICSM.2015.7332513 · DOI
  9. choetkiertikul, 2018, A deep learning model for estimating story points, IEEE Transactions on Software Engineering, 1
  10. sutskever, 2014, Sequence to sequence learning with neural networks, CoRR, abs 1409 3215
  11. 10.1145/3238147.3240732 · DOI
  12. 10.1145/2884781.2884804 · DOI · Paper page
  13. 10.1145/2786805.2786849 · DOI · Paper page
  14. 10.1145/2970276.2970326 · DOI · Paper page
  15. 10.1145/2786805.2786849 · DOI · Paper page
  16. 10.1109/MSR.2015.38 · DOI · Paper page
  17. 10.1109/ASE.2013.6693113 · DOI · Paper page
  18. allamanis, 2016, A convolutional attention network for extreme summarization of source code, CoRR, abs 1602 3001
  19. wu, 2016, Google's neural machine translation system: Bridging the gap between human and machine translation, CoRR, abs 1609 8144
  20. 0, Android Add Catch Block
  21. 0, Android Abstract Method
  22. 0, Google Return Value
  23. 0, Ovirt Anonymous Class To Lambda
  24. 0, On learning meaningful code changes via neural machine translation Replication Package
  25. 0, Ovirt Redundant Super
  26. 0, Ovirt Flipped Parameters
  27. 10.1145/2950290.2983951 · DOI
  28. 0, Ovirt Rename Method
  29. 10.1145/3106237.3117776 · DOI
  30. 10.1109/ICSME.2017.46 · DOI · Paper page
  31. 10.1109/ICPC.2016.7503707 · DOI · Paper page
  32. 10.1109/ICSME.2017.79 · DOI
  33. 10.1145/2666356.2594321 · DOI · Paper page
  34. parr, 2013, The Definitive Antlr 4 Reference
  35. 2018, How many words are there in the english language?
  36. 10.1109/TSE.2018.2844788 · DOI · Paper page
  37. 10.18653/v1/P16-2021 · DOI
  38. 0, Android Remove Synchronized From Signature
  39. 0, Android Remove Synchronized
  40. 10.1145/3180155.3180167 · DOI · Paper page
  41. 0, Android Rename Parameter
  42. 0, Android Return Value
  43. 0, Gerrit - Android
  44. 0, Gerrit - Google Source
  45. 0, Gerrit - Ovirt
  46. 0, Gerrit
  47. 0, Google Broader Generic Type
  48. 0, Google Narrowing Visibility
  49. 0, Android Added Null Check
  50. 0, Android Add Final
  51. 0, Android Change Operand
  52. 0, Android Broadening Visibility
  53. 0, Android Move Synchronization
  54. 0, Android Merging Catch Blocks
  55. 10.1109/ASE.2015.73 · DOI · Paper page
  56. 0, Android Narrow Catch Block
  57. høst, 2009, Debugging method names, ECOOP 2009 - Object-Oriented Programming, 294, 10.1007/978-3-642-03013-0_14 · DOI · Paper page
  58. kalchbrenner, 2013, Recurrent continuous translation models, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1700
  59. 10.1109/ASE.2017.8115626 · DOI · Paper page
  60. 10.1109/ICSE.2017.9 · DOI · Paper page
  61. 10.1145/2950290.2950334 · DOI · Paper page
  62. 10.1109/ICSME.2017.52 · DOI · Paper page
  63. gupta, 2017, Deepfix: Fixing common c language errors by deep learning, AAAI, 10.1609/aaai.v31i1.10742 · DOI · Paper page

Cited by

See all 207

Metadata

Authors
Tufano, M., Pantiuchina, J., Watson, C., Bavota, G., & Poshyvanyk, D.
Venue
2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)
Publisher
IEEE
Published
2019-05
Pages
25-36
DOI
10.1109/icse.2019.00021
OpenAlex
W2954823997
Cited by
207
References
6
FWCI
21.76
Type
conference paper
Language
en
Open access
closed
Licence

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 Learning Meaningful Code Changes Via Neural Machine Translation. https://app.cochat.ai/papers/10.1109/icse.2019.00021
The paper
Tufano, M., Pantiuchina, J., Watson, C., Bavota, G., & Poshyvanyk, D. (2019). On Learning Meaningful Code Changes Via Neural Machine Translation. 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE). https://doi.org/10.1109/icse.2019.00021

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.