A Structured Connectionist Approach to Inferencing and Retrieval

Lange, Trent E.

doi:10.1007/978-0-585-29599-2_3

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synchrony can also be augmented by propagating activity patterns that are distributed both temporally and spatially. Such patterns have been referred to as "signatures" (Lange & Dyer 1989;Lange & Wharton 1995) and, when encoded as distributed representations, they can be learned and can also control their own propagation (Sumida & Dyer 1992).…”

Section: Michael G Dyermentioning

confidence: 99%

Distributed neural blackboards could be more attractive

Grüning¹,

Treves²

2006

Behav Brain Sci

View full text Add to dashboard Cite

Human cognition is unique in the way in which it relies on combinatorial (or compositional) structures. Language provides ample evidence for the existence of combinatorial structures, but they can also be found in visual cognition. To understand the neural basis of human cognition, it is therefore essential to understand how combinatorial structures can be instantiated in neural terms. In his recent book on the foundations of language, Jackendoff described four fundamental problems for a neural instantiation of combinatorial structures: the massiveness of the binding problem, the problem of 2, the problem of variables, and the transformation of combinatorial structures from working memory to long-term memory. This paper aims to show that these problems can be solved by means of neural "blackboard" architectures. For this purpose, a neural blackboard architecture for sentence structure is presented. In this architecture, neural structures that encode for words are temporarily bound in a manner that preserves the structure of the sentence. It is shown that the architecture solves the four problems presented by Jackendoff. The ability of the architecture to instantiate sentence structures is illustrated with examples of sentence complexity observed in human language performance. Similarities exist between the architecture for sentence structure and blackboard architectures for combinatorial structures in visual cognition, derived from the structure of the visual cortex. These architectures are briefly discussed, together with an example of a combinatorial structure in which the blackboard architectures for language and vision are combined. In this way, the architecture for language is grounded in perception. Perspectives and potential developments of the architectures are discussed.

show abstract

Section: Michael G Dyermentioning

confidence: 99%

Distributed neural blackboards could be more attractive

Grüning¹,

Treves²

2006

Behav Brain Sci

View full text Add to dashboard Cite

show abstract

“…The propagation mechanism is extremely simple, but unfortunately, also fragile due to no prior knowledge being incorporated into the systems. Lange [24] describes a structured localized connectionist model ROBIN which explores the integration of language understanding and episodic memory retrieval in a single spreading activation mechanism. ROBIN is capable of using the constraint satisfaction of evidential activation in combination with its parallel dynamic inferencing.…”

Section: Comparison With Other Connectionist and Hybrid Systemsmentioning

confidence: 99%

Symbolic connectionism in natural language disambiguation

Chan

Franklin²

1998

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-Natural language understanding involves the simultaneous consideration of a large number of different sources of information. Traditional methods employed in language analysis have focused on developing powerful formalisms to represent syntactic or semantic structures along with rules for transforming language into these formalisms. However, they make use of only small subsets of knowledge. This article will describe how to use the whole range of information through a neurosymbolic architecture which is a hybridization of a symbolic network and subsymbol vectors generated from a connectionist network. Besides initializing the symbolic network with prior knowledge, the subsymbol vectors are used to enhance the system's capability in disambiguation and provide flexibility in sentence understanding. The model captures a diversity of information including word associations, syntactic restrictions, case-role expectations, semantic rules and context. It attains highly interactive processing by representing knowledge in an associative network on which actual semantic inferences are performed. An integrated use of previously analyzed sentences in understanding is another important feature of our model. The model dynamically selects one hypothesis among multiple hypotheses. This notion is supported by three simulations which show the degree of disambiguation relies both on the amount of linguistic rules and the semantic-associative information available to support the inference processes in natural language understanding. Unlike many similar systems, our hybrid system is more sophisticated in tackling language disambiguation problems by using linguistic clues from disparate sources as well as modeling context effects into the sentence analysis. It is potentially more powerful than any systems relying on one processing paradigm.Index Terms-Bayesian network, constraint satisfaction, hybrid systems, natural language understanding, neural network applications, semantic analysis. I. APPEAL OF SYMBOLIC CONNECTIONISMIN LANGUAGE UNDERSTANDING C OGNITIVE linguists view language as a conventional system for coding communicative intent and grammar as a schematic coding system that is induced from a large number of semantic associations and rules of meaning [22], [23]. They have sought to show that neither the form nor the meaning of expressions can be adequately described without reference to speakers' encyclopedic knowledge, their construction of mental models, and their ability to map concepts Parallel constraint satisfaction can in principle capture the most striking aspect of human expert performance: experts tend to arrive quickly at a small number of the best solutions to a problem, without serial search through alternative possibilities. Connectionism is in a position to account for the behavior of both regular and irregular patterns.While current research appears to indicate that the connectionist approach may be better for modeling many cognitive processes and it seems there is a developing trend in applying conne...

show abstract

“…Associative mechanisms help to retrieve relevant knowledge given inputs that are similar to, or have some relationship to, previously stored memories. For example, Lange (1994) describes a structured connectionist model that is capable of episodic reminding. When given the input cue…”

Section: A Connectionist Perspectivementioning

confidence: 99%

Trajectories through Knowledge Space

Bookman

1994

View full text Add to dashboard Cite

A Structured Connectionist Approach to Inferencing and Retrieval

Cited by 7 publications

References 17 publications

Distributed neural blackboards could be more attractive

Distributed neural blackboards could be more attractive

Symbolic connectionism in natural language disambiguation

Trajectories through Knowledge Space

Contact Info

Product

Resources

About