A Solution to the Binding Problem for Compositional Connectionism
A Solution to the Binding Problem for Compositional Connectionism
复制标题
组合联结主义绑定问题的解决方案
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
D. Kalar
中科院分区：
文献类型：
--
作者：
J. Hummel;K. Holyoak;C. Green;L. Doumas;Derek Devnich;A. Kittur;D. Kalar
实现组合连接主义意味着找到一种在连接主义系统中表示角色填充者绑定而不牺牲角色填充者独立性的方法。基于各种连词编码的角色-填充者绑定方案（连接主义文献中最常见的方法）未能保持角色-填充者的独立性。同时，角色到填充器的动态绑定（例如，通过同步触发）在不牺牲独立性的情况下表示绑定，但不适合将绑定存储在长期记忆中。动态绑定（用于工作记忆中的表示）和连接编码（用于长期存储和标记形成）的适当组合为组合连接主义提供了一个平台，并且在模拟人类感知和认知的许多方面已被证明是成功的。组合系统将有限数量的代表性元素（符号或子符号）组合并重新组合成更大数量的特定结构（如果允许递归，则是无限的）。例子包括自然语言和形式符号系统（例如，命题符号、数学符号和计算机编程语言）。组成系统的一个重要特性是，结构中单个元素的意义和表现形式不会随着它们在整体结构中的位置而变化。例如，“爱”、“约翰”和“玛丽”可以组合成两个不同的命题，爱（约翰，玛丽）和爱（玛丽，约翰）。这些元素（可以是对象、关系或关系角色）的意义和表现从根本上独立于每个元素在整体构图结构中的位置（例如，无论玛丽是爱人还是被爱人，她的表现方式都是一样的）。与此同时，组合结构的意义确实取决于元素的配置，即。参数（这里是John和Mary）到关系角色（lover和beloved）的绑定。版权所有©2004，美国人工智能协会（www.aaai.org）。版权所有。正式组合系统的这一基本属性很容易被忽视。然而，这是必要的：如果一个元素（角色或对象）的表示随着函数的变化而改变它所绑定的参数或角色，那么结果系统就不能被恰当地描述为“组合”：由“相同”符号组成的不同表达式不会由相同的符号组成；它们会是不同的表达方式和不同的符号。它们只是不同，没有系统上的共同点。角色填充独立性的重要性在人类关系推理中是显而易见的。关系概括——依赖于对象之间的关系而不仅仅是这些对象的特征的推论和概括——只有在关系角色独立于其填充物的情况下才有可能（Hummel & Holyoak, 1997,2003）。例如，假设有人知道约翰爱玛丽，玛丽爱扎克，而约翰嫉妒扎克。然后这个人观察到莎莉爱汤姆，而汤姆爱辛迪。一个似是而非的类比推论是莎莉会嫉妒辛迪。这个推论是基于John对Sally、Mary对Tom、Zack对Cindy的关系对应（即参与相应的角色）。进行推理需要推理者发现这些对应关系，并利用它们来指导对第二种（新）情况的推理（例如，汤姆会嫉妒莎莉不是一个合理的推断）。重要的是，只有当爱情关系无论谁爱谁都以同样的方式表现（即独立于其填充物），并且所涉及的人独立于他们的角色绑定（例如，同一个玛丽既是爱人又是被爱的人；见Hummel & Holyoak， 2003），才有可能发现和使用对应关系。
Achieving compositional connectionism means finding a way to represent role-filler bindings in a connectionist system without sacrificing role-filler independence. Role-filler binding schemes based on varieties of conjunctive coding (the most common approach in the connectionist literature) fail to preserve role-filler independence. At the same time, dynamic binding of roles to fillers (e.g., by synchrony of firing) represents bindings without sacrificing independence, but is inadequate for storing bindings in long-term memory. An appropriate combination of dynamic binding (for representation in working memory) and conjunctive coding (for long-term storage and token formation) provides a platform for compositional connectionism, and has proven successful in simulating numerous aspects of human perception and cognition. Compositional Systems, Role-Filler Independence and Binding Compositional systems combine and recombine a finite number of representational elements (symbols or subsymbols) into a much larger (infinite, if recursion is permitted) number of specific structures. Examples include natural languages and formal symbol systems (e.g., propositional notation, mathematical notation, and computer programming languages). An important property of a compositional system is that the meaning and representation of individual elements in a structure do not vary as a function of their position in the structure as a whole. For example, “loves,” “John” and “Mary” can be combined to form two different propositions, loves (John, Mary) and loves (Mary, John). The meaning and representation of these elements (which can be objects, relations or relational roles) is fundamentally independent of each element’s place in the compositional structure as a whole (e.g.,, Mary is represented in the same way whether she is a lover or a beloved). At the same time, the meaning of the compositional structure does depend on the elements’ configuration—i.e., the bindings of arguments (here, John and Mary) to relational roles (lover and beloved). Copyright © 2004, American Association for Artificial Intelligence (www.aaai.org). All rights reserved. Role-Filler Independence This property of formal compositional systems is so fundamental that it is easy to overlook. Yet it is essential: If the representation of an element (role or object) varied as a function the argument or role to which it was bound, then the resulting system would not be properly described as “compositional”: Different expressions consisting of the “same” symbols would not consist of the same symbols; they would be different expressions with different symbols. They would simply be different, with nothing systematic in common. The importance of role-filler independence is apparent in human relational reasoning. Relational generalization—inferences and generalizations that depend on relations between objects rather than just the features of those objects—is only possible if relational roles are represented independently of their fillers (Hummel & Holyoak, 1997, 2003). For example, suppose someone knows that John loves Mary, Mary loves Zack, and John is jealous of Zack. This person then observes that Sally loves Tom, and Tom loves Cindy. A plausible analogical inference is that Sally will be jealous of Cindy. This inference is based on the relational correspondences (i.e., participation in corresponding roles) of John to Sally, Mary to Tom, and Zack to Cindy. Making the inference requires the reasoner to discover these correspondences and to use them to guide inferences about the second (novel) situation (e.g., it is not a plausible inference that Tom will be jealous of Sally). Importantly, it is only possible to discover and use the correspondences if the loves relation is represented in the same way regardless of who loves whom (i.e., independently of its fillers), and the people involved are represented independently of their role bindings (e.g., the same Mary is both a lover and beloved; see Hummel & Holyoak, 2003).