Automatic documentation generation tools, or auto docs, are widely used to visualize information about APIs. However, each auto doc tool comes with its own unique representation of API information. In this paper, I use an information visualization analysis of auto docs to generate potential design principles for improving their usability. Developers use auto docs as a reference by looking up relevant API primitives given partial information, or leads, about its name, type, or behavior. I discuss how auto docs can better support searching and scanning on these leads, e.g. by providing more information-dense visualizations of method signatures.
Source code documentation is an important artifact for efficient software development. Code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive. In this paper, we employed Codex for automatic code documentation creation. Codex is a GPT-3 based model pre-trained on both natural and programming languages. We find that Codex outperforms existing techniques even with basic settings like one-shot learning (i.e., providing only one example for training). Codex achieves an overall BLEU score of 20.6 for six different programmi…
Code example is a crucial part of good documentation. It helps the developers to understand the documentation easily and use the corresponding code unit (e.g., method) properly. However, many official documentation still lacks (good) code example and it is one of the common documentation issues as found by several studies. Hence in this paper, we consider automatic code example generation for documentation, a direction less explored by the existing research. We employ Codex, a GPT-3 based model, pre-trained on both natural and programming languages to generate code examples from source code an…
Generating and maintaining API documentation with integrity and consistency can be time-consuming and expensive for evolving APIs. To solve this problem, several approaches have been proposed to automatically generate high-quality API documentation based on a combination of knowledge from different web sources. However, current researches are weak in handling unpopular APIs and cannot generate structured API documentation. Hence, in this poster, we propose a hybrid technique(namely \textit{gDoc}) for the automatic generation of structured API documentation. We first present a fine-grained sear…
An application's user documentation, also referred to as the user manual, is one of the core elements required in application distribution. While there exist many tools to aid an application's developer in creating and maintaining documentation on and for the code itself, there are no tools that complement code development with user documentation for modern graphical applications. Approaches like literate programming are not applicable to this scenario, as not a library, but a full application is to be documented to an end-user. Documentation generation on applications up to now was only parti…
University of Waterloo（滑铁卢大学）；IBM Research（IBM研究院）；University of Michigan（密歇根大学）；IBM Research Europe（IBM欧洲研究院）；JD.COM Silicon Valley Research Center（京东硅谷研究中心）
Jupyter notebook allows data scientists to write machine learning code together with its documentation in cells. In this paper, we propose a new task of code documentation generation (CDG) for computational notebooks. In contrast to the previous CDG tasks which focus on generating documentation for single code snippets, in a computational notebook, one documentation in a markdown cell often corresponds to multiple code cells, and these code cells have an inherent structure. We proposed a new model (HAConvGNN) that uses a hierarchical attention mechanism to consider the relevant code cells and …
Software projects capture information in various kinds of artifacts, including source code, tests, and documentation. Such artifacts routinely encode information that is redundant, i.e., when a specification encoded in the source code is also separately tested and documented. Without supporting technology, such redundancy easily leads to inconsistencies and a degradation of documentation quality. We designed a tool-supported technique, called DScribe, that leverages redundancy between tests and documentation to generate consistent and checkable documentation and unit tests based on a single so…
Machine Learning software documentation is different from most of the documentations that were studied in software engineering research. Often, the users of these documentations are not software experts. The increasing interest in using data science and in particular, machine learning in different fields attracted scientists and engineers with various levels of knowledge about programming and software engineering. Our ultimate goal is automated generation and adaptation of machine learning software documents for users with different levels of expertise. We are interested in understanding the n…
Kent State University（肯特州立大学）；Microsoft（微软）；Georgia Institute of Technology（佐治亚理工学院）
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing the documentation code pairs by embedding them into latent space, without the association of external knowledge. In this paper, we propose a generation-augmented query expansion framework. Inspired by the human retrieval process - sketching an answer before searching, in this work, we utilize the powerful code generation model to benefit the code retrieval tas…
Application of formal models provides many benefits for the software and system development, however, the learning curve of formal languages could be a critical factor for an industrial project. Thus, a natural language specification that reflects all the aspects of the formal model might help to understand the model and be especially useful for the stakeholders who do not know the corresponding formal language. Moreover, an automated generation of the documentation from the model would replace manual updates of the documentation for the cases the model is modified. This paper presents an ongo…
Understanding or comprehending source code is one of the core activities of software engineering. Understanding object-oriented source code is essential and required when a programmer maintains, migrates, reuses, documents or enhances source code. The source code that is not comprehended cannot be changed. The comprehension of object-oriented source code is a difficult problem solving process. In order to document object-oriented software system there are needs to understand its source code. To do so, it is necessary to mine source code dependencies in addition to quantitative information in s…
Testing is widely recognized as an important stage of the software development lifecycle. Effective software testing can provide benefits such as bug finding, preventing regressions, and documentation. In terms of documentation, unit tests express a unit's intended functionality, as conceived by the developer. A test oracle, typically expressed as an condition, documents the intended behavior of a unit under a given test prefix. Synthesizing a functional test oracle is a challenging problem, as it must capture the intended functionality rather than the implemented functionality. In this paper,…
Optimizing and maintaining up-to-date API documentation is a challenging problem for evolving OpenAPIs. In this poster, we propose a data-driven continuous optimization solution and multilingual SDK generation scheme to improve the comprehensibility of API documentation. We compute the correlation between API integrity and API trial success rate. Based on this, we partition the API to ensure that each API has a correct optimization direction. Then, we propose a fine-grained(i.e., parameter level) continuous optimization solution to annotate problems in API documents in real-time. Based on the …
University of British Columbia Okanagan（不列颠哥伦比亚大学奥肯那根分校）
Code comments are significantly helpful in comprehending software programs and also aid developers to save a great deal of time in software maintenance. Code comment generation aims to automatically predict comments in natural language given a code snippet. Several works investigate the effect of integrating external knowledge on the quality of generated comments. In this study, we propose a solution, namely APIContext2Com, to improve the effectiveness of generated comments by incorporating the pre-defined Application Programming Interface (API) context. The API context includes the definition…
Code comments can help in program comprehension and are considered as important artifacts to help developers in software maintenance. However, the comments are mostly missing or are outdated, specially in complex software projects. As a result, several automatic comment generation models are developed as a solution. The recent models explore the integration of external knowledge resources such as Unified Modeling Language class diagrams to improve the generated comments. In this paper, we propose API2Com, a model that leverages the Application Programming Interface Documentations (API Docs) as…
Software documentation is an essential but labor intensive task that often requires a dedicated team of developers to ensure coverage and accuracy. Good documentation will help shorten the development cycle and improve the overall team efficiency as well as maintainability. In today's crowd-driven development environment, good documentation can go a long way in building a developer community from scratch. To that end, we took the first steps in building a tool called Autodoc that can assist software developers in writing better documentation faster. Autodoc goes beyond traditional boilerplate …
