While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating code generation, and it can be difficult to accurately assess code generation performance rigorously. To meet this challenge, we introduce APPS, a benchmark for code generation. Unlike prior work in more restricted settings, our benchmark measures the ability of models to take an arbitrary natural language specification and generate satisfactory Python code. Similar to how companies assess candidate software developers, we then evaluate models by checking their generated code on test cases. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. We fine-tune large language models on both GitHub and our training set, and we find that the prevalence of syntax errors is decreasing exponentially as models improve. Recent models such as GPT-Neo can pass approximately 20% of the test cases of introductory problems, so we find that machine learning models are now beginning to learn how to code. As the social significance of automatic code generation increases over the coming years, our benchmark can provide an important measure for tracking advancements.
We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both "bimodal" and "unimodal" data. Here, bimodal data is the combination of text and corresponding code snippets, whereas unimodal data is merely code snippets. We first evaluate CoTexT with multi-task learning: we perform Code Summarization on 6 different programming languages and Code Refinement on both small and medium size featured in the CodeXGLUE dataset. We further conduct extensive experiments to investigate CoTexT on other tasks within the CodeXGlue dataset, including Code Generation and Defect Detection. We consistently achieve SOTA results in these tasks, demonstrating the versatility of our models.
We take the first step to address the task of automatically generating shellcodes, i.e., small pieces of code used as a payload in the exploitation of a software vulnerability, starting from natural language comments. We assemble and release a novel dataset (Shellcode_IA32), consisting of challenging but common assembly instructions with their natural language descriptions. We experiment with standard methods in neural machine translation (NMT) to establish baseline performance levels on this task.
We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens. The intermediate formal representation is then compiled into target source codes. This abstraction of programming details allows seq2seq networks to learn complex application structures with less overhead. In order to train sequence models, we introduce a data synthesis method grounded in a human survey. We demonstrate that Text2App generalizes well to unseen combination of app components and it is capable of handling noisy natural language instructions. We explore the possibility of creating applications from highly abstract instructions by coupling our system with GPT-3 -- a large pretrained language model. We perform an extensive human evaluation and identify the capabilities and limitations of our system. The source code, a ready-to-run demo notebook, and a demo video are publicly available at \url{https://github.com/text2app/Text2App}.
Now, the pre-training technique is ubiquitous in natural language processing field. ProphetNet is a pre-training based natural language generation method which shows powerful performance on English text summarization and question generation tasks. In this paper, we extend ProphetNet into other domains and languages, and present the ProphetNet family pre-training models, named ProphetNet-X, where X can be English, Chinese, Multi-lingual, and so on. We pre-train a cross-lingual generation model ProphetNet-Multi, a Chinese generation model ProphetNet-Zh, two open-domain dialog generation models ProphetNet-Dialog-En and ProphetNet-Dialog-Zh. And also, we provide a PLG (Programming Language Generation) model ProphetNet-Code to show the generation performance besides NLG (Natural Language Generation) tasks. In our experiments, ProphetNet-X models achieve new state-of-the-art performance on 10 benchmarks. All the models of ProphetNet-X share the same model structure, which allows users to easily switch between different models. We make the code and models publicly available, and we will keep updating more pre-training models and finetuning scripts.
Commit messages have an important impact in software development, especially when working in large teams. Multiple developers who have a different style of writing may often be involved in the same project. For this reason, it may be difficult to maintain a strict pattern of writing informative commit messages, with the most frequent issue being that these messages are not descriptive enough. In this paper we apply neural machine translation (NMT) techniques to convert code diffs into commit messages and we present an improved sketch-based encoder for this task. We split the approach into three parts. Firstly, we focus on finding a more suitable NMT baseline for this problem. Secondly, we show that the performance of the NMT models can be improved by training on examples containing a specific file type. Lastly, we introduce a novel sketch-based neural model inspired by recent approaches used for code generation and we show that the sketch-based encoder significantly outperforms existing state of the art solutions. The results highlight that this improvement is relevant especially for Java source code files, by examining two different datasets introduced in recent years for this task.
Currently, a growing number of mature natural language processing applications make people's life more convenient. Such applications are built by source code - the language in software engineering. However, the applications for understanding source code language to ease the software engineering process are under-researched. Simultaneously, the transformer model, especially its combination with transfer learning, has been proven to be a powerful technique for natural language processing tasks. These breakthroughs point out a promising direction for process source code and crack software engineering tasks. This paper describes CodeTrans - an encoder-decoder transformer model for tasks in the software engineering domain, that explores the effectiveness of encoder-decoder transformer models for six software engineering tasks, including thirteen sub-tasks. Moreover, we have investigated the effect of different training strategies, including single-task learning, transfer learning, multi-task learning, and multi-task learning with fine-tuning. CodeTrans outperforms the state-of-the-art models on all the tasks. To expedite future works in the software engineering domain, we have published our pre-trained models of CodeTrans. https://github.com/agemagician/CodeTrans
The problem of code generation from textual program descriptions has long been viewed as a grand challenge in software engineering. In recent years, many deep learning based approaches have been proposed, which can generate a sequence of code from a sequence of textual program description. However, the existing approaches ignore the global relationships among API methods, which are important for understanding the usage of APIs. In this paper, we propose to model the dependencies among API methods as an API dependency graph (ADG) and incorporate the graph embedding into a sequence-to-sequence (Seq2Seq) model. In addition to the existing encoder-decoder structure, a new module named ``embedder" is introduced. In this way, the decoder can utilize both global structural dependencies and textual program description to predict the target code. We conduct extensive code generation experiments on three public datasets and in two programming languages (Python and Java). Our proposed approach, called ADG-Seq2Seq, yields significant improvements over existing state-of-the-art methods and maintains its performance as the length of the target code increases. Extensive ablation tests show that the proposed ADG embedding is effective and outperforms the baselines.
Code summarization and generation empower conversion between programming language (PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks, e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART's effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus excels even with limited annotations.
With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and many variants have been proposed. Currently, almost all these models assume that the layer order is fixed and kept the same across data samples. We observe that different data samples actually favor different orders of the layers. Based on this observation, in this work, we break the assumption of the fixed layer order in the Transformer and introduce instance-wise layer reordering into the model structure. Our Instance-wise Ordered Transformer (IOT) can model variant functions by reordered layers, which enables each sample to select the better one to improve the model performance under the constraint of almost the same number of parameters. To achieve this, we introduce a light predictor with negligible parameter and inference cost to decide the most capable and favorable layer order for any input sequence. Experiments on 3 tasks (neural machine translation, abstractive summarization, and code generation) and 9 datasets demonstrate consistent improvements of our method. We further show that our method can also be applied to other architectures beyond Transformer. Our code is released at Github.
Recent advancements in natural language processing \cite{gpt2} \cite{BERT} have led to near-human performance in multiple natural language tasks. In this paper, we seek to understand whether similar techniques can be applied to a highly structured environment with strict syntax rules. Specifically, we propose an end-to-end machine learning model for code generation in the Python language built on-top of pre-trained language models. We demonstrate that a fine-tuned model can perform well in code generation tasks, achieving a BLEU score of 0.22, an improvement of 46\% over a reasonable sequence-to-sequence baseline. All results and related code used for training and data processing are available on GitHub.
Benchmark datasets have a significant impact on accelerating research in programming language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster machine learning research for program understanding and generation. CodeXGLUE includes a collection of 10 tasks across 14 datasets and a platform for model evaluation and comparison. CodeXGLUE also features three baseline systems, including the BERT-style, GPT-style, and Encoder-Decoder models, to make it easy for researchers to use the platform. The availability of such data and baselines can help the development and validation of new methods that can be applied to various program understanding and generation problems.
Focal-plane Sensor-processors (FPSPs) are a camera technology that enable low power, high frame rate computation, making them suitable for edge computation. Unfortunately, these devices' limited instruction sets and registers make developing complex algorithms difficult. In this work, we present Cain - a compiler that targets SCAMP-5, a general-purpose FPSP - which generates code from multiple convolutional kernels. As an example, given the convolutional kernels for an MNIST digit recognition neural network, Cain produces code that is half as long, when compared to the other available compilers for SCAMP-5.
Annotated data has become the most important bottleneck in training accurate machine learning models, especially for areas that require domain expertise. A recent approach to deal with the above issue proposes using natural language explanations instead of labeling individual data points, thereby increasing human annotators' efficiency as well as decreasing costs substantially. This paper focuses on the task of turning these natural language descriptions into Python labeling functions by following a novel approach to semantic parsing with pre-trained text-to-text Transformers. In a series of experiments our approach achieves a new state of the art on the semantic parsing benchmark CoNaLa, surpassing the previous best approach by 3.7 BLEU points. Furthermore, on a manually constructed dataset of natural language descriptions-labeling functions pairs we achieve a BLEU of 0.39. Our approach can be regarded as a stepping stone towards models that are taught how to label in natural language, instead of being provided specific labeled samples. Our code, constructed dataset and models are available at https://github.com/ypapanik/t5-for-code-generation.
Deep learning models typically use single-precision (FP32) floating point data types for representing activations and weights, but a slew of recent research work has shown that computations with reduced-precision data types (FP16, 16-bit integers, 8-bit integers or even 4- or 2-bit integers) are enough to achieve same accuracy as FP32 and are much more efficient. Therefore, we designed fbgemm, a high-performance kernel library, from ground up to perform high-performance quantized inference on current generation CPUs. fbgemm achieves efficiency by fusing common quantization operations with a high-performance gemm implementation and by shape- and size-specific kernel code generation at runtime. The library has been deployed at Facebook, where it delivers greater than 2x performance gains with respect to our current production baseline.
Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks. As a result, models for this application usually need additional prior knowledge to be built into the architecture or algorithm. The increased dependency on human experts hinders automation and raises the development and maintenance costs in practice. This work investigates whether a generic transformer-based seq2seq model can achieve competitive performance with minimal code-generation-specific inductive bias design. By exploiting a relatively sizeable monolingual corpus of the target programming language, which is cheap to mine from the web, we achieved 81.03% exact match accuracy on Django and 32.57 BLEU score on CoNaLa. Both are SOTA to the best of our knowledge. This positive evidence highlights a potentially easier path toward building accurate semantic parsers in practice.
Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative hash codes for images associated with multiple semantics for two main reasons, 1) similarity constraints designed in most of the existing methods are based upon an oversimplified similarity assignment(i.e., 0 for instance pairs sharing no label, 1 for instance pairs sharing at least 1 label), 2) the exploration in multi-semantic relevance are insufficient or even neglected in many of the existing methods. These problems significantly limit the discrimination of generated hash codes. In this paper, we propose a novel self-supervised asymmetric deep hashing method with a margin-scalable constraint(SADH) approach to cope with these problems. SADH implements a self-supervised network to sufficiently preserve semantic information in a semantic feature dictionary and a semantic code dictionary for the semantics of the given dataset, which efficiently and precisely guides a feature learning network to preserve multilabel semantic information using an asymmetric learning strategy. By further exploiting semantic dictionaries, a new margin-scalable constraint is employed for both precise similarity searching and robust hash code generation. Extensive empirical research on four popular benchmarks validates the proposed method and shows it outperforms several state-of-the-art approaches.
In this paper, we illustrate how to enhance an existing state-of-the-art modeling language and tool for the Internet of Things (IoT), called ThingML, to support machine learning on the modeling level. To this aim, we extend the Domain-Specific Language (DSL) of ThingML, as well as its code generation framework. Our DSL allows one to define things, which are in charge of carrying out data analytics. Further, our code generators can automatically produce the complete implementation in Java and Python. The generated Python code is responsible for data analytics and employs APIs of machine learning libraries, such as Keras, Tensorflow and Scikit Learn. Our prototype is available as open source software on Github.
In recent years, the use of deep learning in language models gained much attention. Some research projects claim that they can generate text that can be interpreted as human-writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the Machine Learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the Deep-Learning-enabled language models approach, we detected a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like AWD-LSTMs, AWD-QRNNs, and Transformer while using transfer learning and different tokenizations to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach's different strengths and weaknesses and what gaps we find to evaluate the language models or apply them in a real programming context.
Detecting Graphical User Interface (GUI) elements in GUI images is a domain-specific object detection task. It supports many software engineering tasks, such as GUI animation and testing, GUI search and code generation. Existing studies for GUI element detection directly borrow the mature methods from computer vision (CV) domain, including old fashioned ones that rely on traditional image processing features (e.g., canny edge, contours), and deep learning models that learn to detect from large-scale GUI data. Unfortunately, these CV methods are not originally designed with the awareness of the unique characteristics of GUIs and GUI elements and the high localization accuracy of the GUI element detection task. We conduct the first large-scale empirical study of seven representative GUI element detection methods on over 50k GUI images to understand the capabilities, limitations and effective designs of these methods. This study not only sheds the light on the technical challenges to be addressed but also informs the design of new GUI element detection methods. We accordingly design a new GUI-specific old-fashioned method for non-text GUI element detection which adopts a novel top-down coarse-to-fine strategy, and incorporate it with the mature deep learning model for GUI text detection.Our evaluation on 25,000 GUI images shows that our method significantly advances the start-of-the-art performance in GUI element detection.