Text2App：一个从文本描述创建Android应用的框架
Text2App: A Framework for Creating Android Apps from Text Descriptions
摘要：
我们提出了Text 2App--一个允许用户从自然语言规范创建功能性Android应用程序的框架。传统的源代码生成方法试图直接生成源代码，这对于创建复杂的软件是不切实际的。我们克服了这个限制，通过将自然语言转换成一个抽象的中间形式语言表示一个应用程序的令牌数量少得多。然后将中间形式表示编译成目标源代码。这种编程细节的抽象允许seq 2seq网络以更少的开销学习复杂的应用程序结构。为了训练序列模型，我们介绍了一种基于人类调查的数据合成方法。我们证明，Text 2App的推广，以及看不见的应用程序组件的组合，它是能够处理嘈杂的自然语言指令。我们探索通过将我们的系统与GPT-3（一种大型预训练的语言模型）耦合，从高度抽象的指令创建应用程序的可能性。我们进行了广泛的人工评估，并确定了我们系统的能力和局限性。在\url{https://github.com/text2app/Text2App}上可以公开获得源代码、一个随时可以运行的演示笔记本和一个演示视频。
英文摘要：
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}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
