Context-free parsing with connectionist networks

Fanty, Mark

doi:10.1063/1.36271

Cited by 38 publications

(33 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way of approaching the problem of dealing with recursion in connectionist models is to "hardwire" symbolic structures directly into the architecture of the network (e.g., Fanty, 1985;McClelland & Kawamoto, 1986;Miyata, Smolensky & Legendre, 1993;Small, Cottrell & Shastri, 1982). The network can therefore be viewed as a non-standard implementation of a symbolic system, and can solve the problem of dealing with recursive natural language structures by virtue of its symbol processing abilities, just as do standard symbolic systems in computational linguistics.…”

Section: Connectionism and Recursionmentioning

confidence: 99%

Toward a Connectionist Model of Recursion in Human Linguistic Performance

Christiansen¹,

1999

View full text Add to dashboard Cite

Naturally occurring speech contains only a limited amount of complex recursive structure, and this is reflected in the empirically documented difficulties that people experience when processing such structures. We present a connectionist model of human performance in processing recursive language structures. The model is trained on simple artificial languages. We find that the qualitative performance profile of the model matches human behavior, both on the relative difficulty of center-embedding and crossdependency, and between the processing of these complex recursive structures and right-branching recursive constructions. We analyze how these differences in performance are reflected in the internal representations of the model by performing discriminant analyses on these representations both before and after training. Furthermore, we show how a network trained to process recursive structures can also generate such structures in a probabilistic fashion. This work suggests a novel explanation of people's limited recursive performance, without assuming the existence of a mentally represented competence grammar allowing unbounded recursion.

show abstract

Section: Connectionism and Recursionmentioning

confidence: 99%

Toward a Connectionist Model of Recursion in Human Linguistic Performance

Christiansen¹,

1999

View full text Add to dashboard Cite

show abstract

“…The units represent symbols or concepts drawn from either symbolic grammar rules [4,5,6,7], word senses, syntactic roles or semantic roles [8,9,10]. Many distributed parsing models employing a single neural network have also been developed, using either an FF-MLP network [11,12], an SRN [13,14] or a fully recurrent network [15].…”

Section: Singular Architecturesmentioning

confidence: 99%

Connectionist natural language parsing

Palmer-Brown

Tepper

Powell

2002

Trends in Cognitive Sciences

View full text Add to dashboard Cite

Teaser: The extent to which connectionist systems have succeeded in parsing a wide range of realistic sentences, containing syntactic structures that are commonly found in natural language interaction, is reviewed, and an assessment is made of their ability to model human sentence processing.Keywords: connectionism, neural networks, parsing, syntactic processing, corpus. SummaryThe key developments of two decades of connectionist parsing are reviewed. Connectionist parsers are assessed according to their ability to automatically learn from examples to represent syntactic structures, without being presented with symbolic grammar rules. This review also considers the extent to which connectionist parsers offer computational models of human sentence processing and provide plausible accounts of psycholinguistic data. In considering these issues, special attention is paid to the level of realism, the nature of the modularity, and the type of processing that is to be found in a wide range of parsers.

show abstract

“…In view of the difficulty of the problem, much early work "hand-wired" symbolic structures into the network architecture (e.g., Fanty, 1985;McClelland & Kawamoto, 1986;Miyata, Smolensky & Legendre, 1993;Small, Cottrell & Shastri, 1982). Such connectionist re-implementations of symbolic systems can have interesting computational properties and may be illuminating regarding the viability of a particular style of symbolic model for distributed computation (Chater & Oaksford, 1990).…”

Section: Sentence Processingmentioning

confidence: 99%

Connectionist natural language processing: the state of the art

Christiansen¹

1999

Cognitive Science

View full text Add to dashboard Cite

This Special Issue on Connectionist Models of Human Language Processing provides an opportunity for an appraisal both of specific connectionist models and of the status and utility of connectionist models of language in general. This introduction provides the background for the papers in the Special Issue. The development of connectionist models of language is traced, from their intellectual origins, to the state of current research. Key themes that arise throughout different areas of connectionist psycholinguistics are highlighted, and recent developments in speech processing, morphology, sentence processing, language production, and reading are described. We argue that connectionist psycholinguistics has already had a significant impact on the psychology of language, and that connectionist models are likely to have an important influence on future research.

show abstract

Context-free parsing with connectionist networks

Cited by 38 publications

References 3 publications

Toward a Connectionist Model of Recursion in Human Linguistic Performance

Toward a Connectionist Model of Recursion in Human Linguistic Performance

Connectionist natural language parsing

Connectionist natural language processing: the state of the art

Contact Info

Product

Resources

About