用程序合成方法自动生成抽象推理题，提升模型解题能力
Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task Generation
- 基于类型化领域语言构建可解释程序解法
- 利用失败案例生成数万道带正确解的合成题目
- 适合研究可解释人工智能与自动推理的学者
抽象思维和类比推理是快速适应新环境、分解未知问题并综合知识解决复杂任务的关键。本文提出TransCoder，一种基于神经程序合成的抽象问题求解方法，并对生成模块的决策过程进行系统分析。该框架核心是一种类型化的领域专用语言，便于特征工程与抽象推理。训练时，将未能解决的任务转化为新任务，构建合成数据集；每个合成任务均配有已知程序解，模型以监督方式训练。解法以透明的程序形式表示，可检查与验证。在抽象推理语料库（Abstract Reasoning Corpus）上验证，该框架生成了数万道合成问题及对应解，推动学习系统的系统性进展。
原文摘要 · Abstract (English)
The ability to think abstractly and reason by analogy is a prerequisite to rapidly adapt to new conditions, tackle newly encountered problems by decomposing them, and synthesize knowledge to solve problems comprehensively. We present TransCoder, a method for solving abstract problems based on neural program synthesis, and conduct a comprehensive analysis of decisions made by the generative module of the proposed architecture. At the core of TransCoder is a typed domain-specific language, designed to facilitate feature engineering and abstract reasoning. In training, we use the programs that failed to solve tasks to generate new tasks and gather them in a synthetic dataset. As each synthetic task created in this way has a known associated program (solution), the model is trained on them in supervised mode. Solutions are represented in a transparent programmatic form, which can be inspected and verified. We demonstrate TransCoder's performance using the Abstract Reasoning Corpus dataset, for which our framework generates tens of thousands of synthetic problems with corresponding solutions and facilitates systematic progress in learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。