用于系统性泛化的神经符号递归机
Neural-Symbolic Recursive Machine for Systematic Generalization
- National Key Laboratory of General Artificial Intelligence, BIGAI（北京智源人工智能研究院通用人工智能国家重点实验室）
- Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
- UCLA（加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出神经符号递归机(NSR)，通过集成神经感知、语法解析和语义推理的模块化设计及演绎-溯因算法，在多个基准上实现了卓越的系统性泛化与可迁移性。
AI中文摘要：
当前的学习模型在实现类人系统性泛化方面常常遇到困难，特别是在从有限数据中学习组合规则并将其外推到新组合时。我们提出了神经符号递归机（NSR），其核心是一个基础符号系统（GSS），允许直接从训练数据中产生组合语法和语义。NSR采用模块化设计，集成了神经感知、语法解析和语义推理。这些组件通过一种新颖的演绎-溯因算法协同训练。我们的研究结果表明，NSR的设计赋予了等变性和组合性的归纳偏置，使其具有足够的表现力，能够熟练处理各种序列到序列任务，并实现无与伦比的系统性泛化。我们在四个旨在探测系统性泛化能力的挑战性基准上评估了NSR的有效性：用于语义解析的SCAN、用于字符串操作的PCFG、用于算术推理的HINT，以及一个组合机器翻译任务。结果证实，在泛化能力和可迁移性方面，NSR优于当代的神经模型和混合模型。
英文摘要：
Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbolic Recursive Machine (NSR), whose core is a Grounded Symbol System (GSS), allowing for the emergence of combinatorial syntax and semantics directly from training data. The NSR employs a modular design that integrates neural perception, syntactic parsing, and semantic reasoning. These components are synergistically trained through a novel deduction-abduction algorithm. Our findings demonstrate that NSR's design, imbued with the inductive biases of equivariance and compositionality, grants it the expressiveness to adeptly handle diverse sequence-to-sequence tasks and achieve unparalleled systematic generalization. We evaluate NSR's efficacy across four challenging benchmarks designed to probe systematic generalization capabilities: SCAN for semantic parsing, PCFG for string manipulation, HINT for arithmetic reasoning, and a compositional machine translation task. The results affirm NSR's superiority over contemporary neural and hybrid models in terms of generalization and transferability.
