CoDesc: A Large Code–Description Parallel Dataset

Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance. However, researchers have yet been able to effectively leverage the intrinsic connection between the two tasks as they train these tasks in a separate or pipeline manner, which means their performance can not be well balanced. In this paper, we propose a novel end-to-end model for the two tasks by introducing an additional code generation task. More specifically, we explicitly exploit the probabilistic correlation between code summarization and code generation with dual learning, and utilize the two encoders for code summarization and code generation to train the code retrieval task via multi-task learning. We have carried out extensive experiments on an existing dataset of SQL and Python, and results show that our model can significantly improve the results of the code retrieval task over the-state-of-art models, as well as achieve competitive performance in terms of BLEU score for the code summarization task.

With the fast development of large software projects, automatic code summarization techniques, which summarize the main functionalities of a piece of code using natural languages as comments, play essential roles in helping developers understand and maintain large software projects. Many research efforts have been devoted to building automatic code summarization approaches. Typical code summarization approaches are based on deep learning models. They transform the task into a sequence-to-sequence task, which inputs source code and outputs summarizations in natural languages. All code summarization models impose different input size limits, such as 50 to 10,000, for the input source code. However, how the input size limit affects the performance of code summarization models still remains under-explored. In this article, we first conduct an empirical study to investigate the impacts of different input size limits on the quality of generated code comments. To our surprise, experiments on multiple models and datasets reveal that setting a low input size limit, such as 20, does not necessarily reduce the quality of generated comments. Based on this finding, we further propose to use function signatures instead of full source code to summarize the main functionalities first and then input the function signatures into code summarization models. Experiments and statistical results show that inputs with signatures are, on average, more than 2 percentage points better than inputs without signatures and thus demonstrate the effectiveness of involving function signatures in code summarization. We also invite programmers to do a questionnaire to evaluate the quality of code summaries generated by two inputs with different truncation levels. The results show that function signatures generate, on average, 9.2% more high-quality comments than full code.

Code search is an essential task in software development. Developers often search the internet and other code databases for necessary source code snippets to ease the development efforts. Code search techniques also help learn programming as novice programmers or students can quickly retrieve (hopefully good) examples already used in actual software projects. Given the recurrence of the code search activity in software development, there is an increasing interest in the research community. To improve the code search experience, the research community suggests many code search tools and techniques. These tools and techniques leverage several different ideas and claim a better code search performance. However, it is still challenging to illustrate a comprehensive view of the field considering that existing studies generally explore narrow and limited subsets of used components. This study aims to devise a grounded approach to understanding the procedure for code search and build an operational taxonomy capturing the critical facets of code search techniques. Additionally, we investigate evaluation methods, benchmarks, and datasets used in the field of code search.

Software developers write a lot of source code and documentation during software development. Intrinsically, developers often recall parts of source code or code summaries that they had written in the past while implementing software or documenting them. To mimic developers' code or summary generation behavior, we propose a retrieval augmented framework, REDCODER, that retrieves relevant code or summaries from a retrieval database and provides them as a supplement to code generation or summarization models. REDCODER has a couple of uniqueness. First, it extends the state-of-the-art dense retrieval technique to search for relevant code or summaries. Second, it can work with retrieval databases that include unimodal (only code or natural language description) or bimodal instances (code-description pairs). We conduct experiments and extensive analysis on two benchmark datasets of code generation and summarization in Java and Python, and the promising results endorse the effectiveness of our proposed retrieval augmented framework.

In this paper, we describe an approach for learning planning domain models directly from natural language (NL) descriptions of activity sequences. The modelling problem has been identified as a bottleneck for the widespread exploitation of various technologies in Artificial Intelligence, including automated planners. There have been great advances in modelling assisting and model generation tools, including a wide range of domain model acquisition tools. However, for modelling tools, there is the underlying assumption that the user can formulate the problem using some formal language. And even in the case of the domain model acquisition tools, there is still a requirement to specify input plans in an easily machine readable format. Providing this type of input is impractical for many potential users. This motivates us to generate planning domain models directly from NL descriptions, as this would provide an important step in extending the widespread adoption of planning techniques. We start from NL descriptions of actions and use NL analysis to construct structured representations, from which we construct formal representations of the action sequences. The generated action sequences provide the necessary structured input for inducing a PDDL domain, using domain model acquisition technology. In order to capture a concise planning model, we use an estimate of functional similarity, so sentences that describe similar behaviours are represented by the same planning operator. We validate our approach with a user study, where participants are tasked with describing the activities occurring in several videos. Then our system is used to learn planning domain models using the participants' NL input. We demonstrate that our approach is effective at learning models on these tasks.

To implement a program functionality, developers can reuse previously written code snippets by searching through a large-scale codebase. Over the years, many code search tools have been proposed to help developers. The existing approaches often treat source code as textual documents and utilize information retrieval models to retrieve relevant code snippets that match a given query. These approaches mainly rely on the textual similarity between source code and natural language query. They lack a deep understanding of the semantics of queries and source code. In this paper, we propose a novel deep neural network named CODEnn (Code-Description Embedding Neural Network). Instead of matching text similarity, CODEnn jointly embeds code snippets and natural language descriptions into a high-dimensional vector space, in such a way that code snippet and its corresponding description have similar vectors. Using the unified vector representation, code snippets related to a natural language query can be retrieved according to their vectors. Semantically related words can also be recognized and irrelevant/noisy keywords in queries can be handled. As a proof-of-concept application, we implement a code search tool named DeepCS using the proposed CODEnn model. We empirically evaluate DeepCS on a large scale codebase collected from GitHub. The experimental results show that our approach can effectively retrieve relevant code snippets and outperforms previous techniques.

Code summarization in software engineering refers to the task of automatically generating short natural language descriptions for source code, which has been addressed by the development of transformer-based models such as CodeBERT, CodeT5, and CodeSearchNet in deep learning. These approaches have played a significant role in enhancing the capability of automated code documentation and producing good summaries. This paper provides an in-depth review of the latest transformer-based models for code summarization in terms of architectures, performance metrics, and diverse applications. Through the analysis of the strengths and weaknesses of these models, we aim to give insights that could guide future research and development in the area of automated code documentation. Through this survey, we will evaluate the progress of transformer-based models and give a foundation for further advancements in code summarization technologies.

Automated code summarization tools allow generating descriptions for code snippets in natural language, which benefits software development and maintenance. Recent studies demonstrate that the quality of generated summaries can be improved by using additional code representations beyond token sequences. The majority of contemporary approaches mainly focus on extracting code syntactic and structural information from abstract syntax trees (ASTs). However, from the view of macro-structures, it is challenging to identify and capture semantically meaningful features due to fine-grained syntactic nodes involved in ASTs. To fill this gap, we investigate how to learn more code semantics and control flow features from the perspective of code statements. Accordingly, we propose a novel model entitled CoSS for code summarization. CoSS adopts a Transformer-based encoder and a graph attention network-based encoder to capture token-level and statement-level semantics from code token sequence and control flow graph, respectively. Then, after receiving two-level embeddings from encoders, a joint decoder with a multi-head attention mechanism predicts output sequences verbatim. Performance evaluations on Java, Python, and Solidity datasets validate that CoSS outperforms nine state-of-the-art (SOTA) neural code summarization models in effectiveness and is competitive in execution efficiency. Further, the ablation study reveals the contribution of each model component.

A framework for the automatic description of healthcare processes in natural language: Application in an aortic stenosis integrated care process.

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 syn-tax, 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.

Code retrieval is to find the code snippet from a large corpus of source code repositories that highly matches the query of natural language description. Recent work mainly uses natural language processing techniques to process both query texts (i.e., human natural language) and code snippets (i.e., machine programming language), however, neglecting the deep structured features of query texts and source codes, both of which contain rich semantic information. In this article, we propose an end-to-end deep graph matching and searching (DGMS) model based on graph neural networks for the task of semantic code retrieval. To this end, we first represent both natural language query texts and programming language code snippets with the unified graph-structured data, and then use the proposed graph matching and searching model to retrieve the best matching code snippet. In particular, DGMS not only captures more structural information for individual query texts or code snippets, but also learns the fine-grained similarity between them by cross-attention based semantic matching operations. We evaluate the proposed DGMS model on two public code retrieval datasets with two representative programming languages (i.e., Java and Python). Experiment results demonstrate that DGMS significantly outperforms state-of-the-art baseline models by a large margin on both datasets. Moreover, our extensive ablation studies systematically investigate and illustrate the impact of each part of DGMS.

Several studies have suggested that comments describing source code can help mitigate the burden of program understanding. However, software systems usually lack adequate comments and even when present, the comments may be obsolete or unhelpful. Researchers have addressed this issue by automatically generating comments from source code, a task referred to as Code Summarization. In this technical presentation, we take a deeper look at some of the significant, recent works in the area of code summarization and how each of them attempts to take a new perspective of this task including methods leveraging RNNs, Transformers, Graph neural networks and Reinforcement learning.

Writing reports by analyzing medical images is error-prone for inexperienced practitioners and time consuming for experienced ones. In this work, we present RepsNet that adapts pre-trained vision and language models to interpret medical images and generate automated reports in natural language. RepsNet consists of an encoder-decoder model: the encoder aligns the images with natural language descriptions via contrastive learning, while the decoder predicts answers by conditioning on encoded images and prior context of descriptions retrieved by nearest neighbour search. We formulate the problem in a visual question answering setting to handle both categorical and descriptive natural language answers. We perform experiments on two challenging tasks of medical visual question answering (VQA-Rad) and report generation (IU-Xray) on radiology image datasets. Results show that RepsNet outperforms state-of-the-art methods with \(81.08 \%\) classification accuracy on VQA-Rad 2018 and 0.58 BLEU-1 score on IU-Xray. Supplementary details are available at: https://sites.google.com/view/repsnet. KeywordsVision and languageVisual question answeringReport generation

Code semantics play a crucial part in code classification, code summarization, code search, and code optimization. This tool has been developed to classify programs based on the high-level logic of the programs. The developed solution uses the idea of supervised learning classification for a set of a labeled dataset of code snippets. The code is vectorized using two novel techniques based on dynamic and static analysis. The former uses a new technique to generate a code vector by approximating the given function using a neural network. The weights of the neural network being the heart of the neural network are used to generate the final vector, which represents the code/function snippet. The latter, i.e. Static Analysis uses the structural information of code to generate the representation. Our two new techniques perform better than the state-of-the-art systems code2vec and neural code comprehension. The obtained accuracies for dynamic and static analysis-based techniques are 98% and 80% respectively. The dynamic model decides the semantics only on the basis of input and output of the programs, hence it can be easily extended to support multiple languages. The dynamic model has been implemented for C++ programs and gives an accuracy of 99% highlighting the easily extendible and language-agnostic feature.

Software development relies heavily on manual processes for transforming requirements into software artifacts such as models, source code, or test cases. Requirements are the starting point for these transformations, and they are typically written in natural language. However, hardly any automated tools exist that translate natural language texts into software artifacts. We propose to adapt recent advances in natural language processing and semantic technologies to generate UML models, test cases, and perhaps even source code, from natural language input. Though earlier efforts in automatic programming had limited success, we are now in a situation where extracting meaning from text has made substantial progress. For example, encouraging results for generating UML models from textual requirements have been achieved. It might even be possible to generate executable test cases. An intermediate step would be to generate tests from API documentation (which would also be a useful capability in itself). An even greater advance would be to automate rote coding. In all of these cases, entirely new classes of software tools would be needed to extract and process the semantics inherent in natural language texts, augment them with tacit knowledge from ontologies and domain models, and, where necessary, ask humans to clarify ambiguities. Though speculative, a determined, long-term effort in translating text to software could automate and accelerate software development to an unprecedented degree.