立场文件：面向词汇任务与转导的广义语法规则及超越经典等变性的基于结构的泛化
Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction
AI总结：
针对神经网络组合泛化能力弱于人类词汇学习的问题，提出基于广义语法规则（GGRs）的通用建模框架，将其作为转导任务中等变性的对应物，可涵盖现有研究并关联强化学习等领域。
摘要：
组合泛化是人类词汇学习区别于当前最优神经网络的核心特性之一。我们提出一个构建可实现组合泛化模型的通用框架，该框架采用广义语法规则（Generalized Grammar Rules，GGRs）——一类用于转导任务的基于对称性的组合约束，我们将其视为物理启发任务中等变性约束在转导领域的对应物。除了形式化语言转导的广义对称性概念外，我们的框架通用性足够强，可将诸多现有研究作为特例纳入其中。我们还提出了GGRs的潜在实现思路，并在此过程中梳理了其与强化学习及其他研究领域的关联。
英文摘要：
Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks. We propose a general framework for building models that can generalize compositionally using the concept of Generalized Grammar Rules (GGRs), a class of symmetry-based compositional constraints for transduction tasks, which we view as a transduction analogue of equivariance constraints in physics-inspired tasks. Besides formalizing generalized notions of symmetry for language transduction, our framework is general enough to contain many existing works as special cases. We present ideas on how GGRs might be implemented, and in the process draw connections to reinforcement learning and other areas of research.
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。
