When deep learning met code search
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of embedding code and natural language queries into real vectors and then using vector distance to approximate semantic correlation between code and the query. Multiple approaches exist for learning these embeddings, including unsupervised techniques, which rely only on a corpus of code examples, and supervised techniques, which use an aligned corpus of paired code and natural language descriptions. The goal of this supervision is to produce embeddings that are more similar for a query and the corresponding desired code snippet.
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.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 10×
“An example of such an RNN is long-short termmemory (LSTM) [18].”
BackgroundMethodInfluentialDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 2×
“In NCS [29], a specific technique named after the general concept of Neural Code Search, the embedding functions Ec and Eq are implemented using a combination of token-level embeddings using fastText [7], which is similar toword2vec [27], and conventional information retrieval techniques, such as TF–IDF [11, 30].”
MethodSequence 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
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 2×
“For this example, we will tokenize based on standard English conventions (e.g. white-space, punctuation) and punctuation relevant to code (e.g. snake and camel case).”
BackgroundMethodTerm-weighting approaches in automatic text retrieval
Salton, G., & Buckley, C. (1988) · Information Processing & Management · doi:10.1016/0306-4573(88)90021-0 · Cited by 9,740
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 3×
“In contrast, a neural network may instead consume the tokens in an input as a sequence, such that the ordering of elements is significant.”
BackgroundMethodLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.1078 · Cited by 3,317 · cited 1×
“A training corpus is used to train the models and may contain duplicate code / natural language pairs.”
Methodcode2vec: Learning distributed representations of code
Alon, U., Zilberstein, M., Levy, O., & Yahav, E. (2019) · Proceedings of the ACM on Programming Languages · doi:10.1145/3290353 · Cited by 962 · cited 2×
“Existing work has introduced neural networks to identify software defects [10], guide program synthesis [5, 35], enable new representations for program analysis [1, 3], facilitate code reuse [17], and automate code changes [34].”
BackgroundMethodLearning to Represent Programs with GraphsPreprint
Allamanis, M., Brockschmidt, M., & Khademi, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00740 · Cited by 840 · cited 1×
“ftware engineering has increased significantly. Existing work has introduced neural networks to identify software defects [10], guide program synthesis[5,35],enablenewrepresentationsforprogramanalysis[1,3],facilitatecodereuse[17],andautomatecodechanges[34].Themodels wepresentheremakeuseofthesetechnologiestovaryingdegr…”
BackgroundInterpretable Convolutional Neural Networks
Zhang, Q., Wu, Y. N., & Zhu, S.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00920 · Cited by 833
Cited by
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Husain, H., Wu, H.-H., Gazit, T., Allamanis, M., & Brockschmidt, M. (2019) · arXiv · doi:10.48550/arxiv.1909.09436 · Cited by 483
“For this, we follow other attempts in the literature [5, 6, 9, 11] and pair functions in open-source software with the natural language present in their respective documentation.”
BackgroundMethodResultInfluentialAn empirical evaluation of GitHub copilot's code suggestions
Nguyen, N., & Nadi, S. (2022) · Proceedings of the 19th International Conference on Mining Software Repositories · doi:10.1145/3524842.3528470 · Cited by 313
Adversarial examples for models of code
Yefet, N., Alon, U., & Yahav, E. (2020) · Proceedings of the ACM on Programming Languages · doi:10.1145/3428230 · Cited by 161
“2017], code search [Cambronero et al. 2019; Liu et al. 2019; Sachdev et al. 2018], and bug finding [Pradel and Sen 2018; Rice et al.”
BackgroundMethodSkCoder: A Sketch-based Approach for Automatic Code Generation
Li, J., Li, Y., Li, G., Jin, Z., Hao, Y., & Hu, X. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00179 · Cited by 64
“We also notice that there are some more advanced code search approaches [21], [22], and they can be applied to our approach in a plug-and-play fashion.”
You see what I want you to see: poisoning vulnerabilities in neural code search
Wan, Y., Zhang, S., Zhang, H., Sui, Y., Xu, G., Yao, D., Jin, H., & Sun, L. (2022) · Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3540250.3549153 · Cited by 60
“Later, a few approaches [5, 11, 15, 38] have been proposed aiming to improve the performance by designing better code representations.”
BackgroundAI in Software Engineering at Facebook
Bader, J., Seohyun Kim, S., Sifei Luan, F., Chandra, S., & Meijer, E. (2021) · IEEE Software · doi:10.1109/ms.2021.3061664 · Cited by 16
Self-citationReACC: A Retrieval-Augmented Code Completion Framework
Lu, S., Duan, N., Han, H., Guo, D., Hwang, S.-W., & Svyatkovskiy, A. (2022) · arXiv · doi:10.48550/arxiv.2203.07722 · Cited by 96
“A common scenario for information retrieval in code domain is code search with natural language description as a query (Arwan et al., 2015; Gu et al., 2018; Cambronero et al., 2019).”
Background
Metadata
- Authors
- Cambronero, J., Li, H., Kim, S., Sen, K., & Chandra, S.
- Venue
- Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
- Publisher
- ACM
- Published
- 2019-08-12
- Pages
- 964-974
- OpenAlex
- W2944246898
- Cited by
- 214
- References
- 30
- FWCI
- 22.38
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.