IntelliCode compose: code generation using transformer

Svyatkovskiy, A.; Deng, Shao Kun; Fu, Sheng-Yu; Sundaresan, Neel

doi:10.1145/3368089.3417058

Cited by 294 publications

(157 citation statements)

References 18 publications

Supporting

Mentioning

157

Contrasting

Order By: Relevance

“…Deep Learning Models of Code : There has been a huge interest in applying deep learning techniques for software engineering tasks such as program functionality classification [10,11,55,75], bug localization [18,29,37,58], code summarization [2,24,66], code clone detection [13,75], program refactoring [32], program translation [12,16], and code synthesis [5,8]. Allamanis et al [3] extend ASTs to graphs by adding a variety of code dependencies as edges among tree nodes, intended to represent code semantics, and apply Gated Graph Neural Networks (GGNN) [49] to learn the graphs; Code2vec [6], Code2seq [4], and ASTNN [75] are designed based on splitting ASTs into smaller ones, either as a bag of path-contexts or as flattened subtrees representing individual statements.…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

Bui¹,

Yu²,

Jiang

2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used in two ways: (1) it can produce vector representation of code which can be applied to code retrieval tasks that do not have labeled data; (2) it can be used in a fine-tuning process for tasks that might still require label data such as code summarization. The key innovation is that we train the source code model by asking it to recognize similar and dissimilar code snippets through a contrastive learning objective. To do so, we use a set of semantic-preserving transformation operators to generate code snippets that are syntactically diverse but semantically equivalent. Through extensive experiments, we have shown that the code models pretrained by Corder substantially outperform the other baselines for code-to-code retrieval, text-to-code retrieval, and code-to-text summarization tasks. CCS Concepts• Software and its engineering → Software libraries and repositories; • Information systems → Information retrieval;

show abstract

Section: Related Workmentioning

confidence: 99%

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

Bui¹,

Yu²,

Jiang

2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…In recent years, several efforts have focused on the use of AI and machine learning techniques for various tasks related to software engineering, including code completion [15,41,75,84], code classification [49,68], API recommendation [16,33], variable and method naming [3,5], type inference [39,93], bug detection and repair [25,40,71,74,89,95], comment description and generation [4,44,48,65,80,91], code change summarization [66], and code clone detection [96]. A significant portion of this work is recounted in Allamanis et al 's survey of the area [2].…”

Section: Ai Techniques For Software Engineeringmentioning

confidence: 99%

Perfection Not Required? Human-AI Partnerships in Code Translation

Weisz¹,

Müller²,

Houde³

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Generative models have become adept at producing artifacts such as images, videos, and prose at human-like levels of proficiency. New generative techniques, such as unsupervised neural machine translation (NMT), have recently been applied to the task of generating source code, translating it from one programming language to another. The artifacts produced in this way may contain imperfections, such as compilation or logical errors. We examine the extent to which software engineers would tolerate such imperfections and explore ways to aid the detection and correction of those errors. Using a design scenario approach, we interviewed 11 software engineers to understand their reactions to the use of an NMT model in the context of application modernization, focusing on the task of translating source code from one language to another. Our threestage scenario sparked discussions about the utility and desirability of working with an imperfect AI system, how acceptance of that system's outputs would be established, and future opportunities for generative AI in application modernization. Our study highlights how UI features such as confidence highlighting and alternate translations help software engineers work with and better understand generative NMT models. CCS CONCEPTS• Human-centered computing → HCI theory, concepts and models; • Software and its engineering → Designing software; • Computing methodologies → Generative and developmental approaches.

show abstract

“…Our code synthesis problem is also related to code completion, i.e., autocompleting the program given the code context (Raychev et al, 2014;Li et al, 2018;Svyatkovskiy et al, 2020). However, standard code completion only requires the model to generate a few tokens following the code context, rather than entire statements.…”

Section: Related Workmentioning

confidence: 99%

PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context

Gong¹,

Cheung²,

Song³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Creating effective visualization is an important part of data analytics. While there are many libraries for creating visualizations, writing such code remains difficult given the myriad of parameters that users need to provide. In this paper, we propose the new task of synthesizing visualization programs from a combination of natural language utterances and code context. To tackle the learning problem, we introduce PLOTCODER, a new hierarchical encoder-decoder architecture that models both the code context and the input utterance. We use PLOTCODER to first determine the template of the visualization code, followed by predicting the data to be plotted. We use Jupyter notebooks containing visualization programs crawled from GitHub to train PLOTCODER. On a comprehensive set of test samples from those notebooks, we show that PLOTCODER correctly predicts the plot type of about 70% samples, and synthesizes the correct programs for 35% samples, performing 3-4.5% better than the baselines. 1

show abstract

IntelliCode compose: code generation using transformer

Cited by 294 publications

References 18 publications

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

Perfection Not Required? Human-AI Partnerships in Code Translation

PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context

Contact Info

Product

Resources

About