19,903 research outputs found
Connectionist natural language parsing
No full textThe key developments of two decades of connectionist parsing are reviewed. Connectionist parsers are assessed according to their ability to learn to represent syntactic structures from examples automatically, 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
Recommended from our members
Large-scale connectionist natural language parsing using lexical semantic and syntactic knowledge
No full textSyntactic parsing plays a pivotal role in most automatic natural language processing systems. The research project presented in this dissertation has focused on two main characteristics of connectionist models for natural language processing: their adaptability to different tagging conventions, and their ability to use multiple linguistic constraints in parallel during sentence processing. In focusing on these key characteristics, an existing hybrid connectionist, shift-reduce corpus-based parsing model has been modified. This parser, which had earlier been trained to acquire linguistic knowledge from the Lancaster Parsed Corpus, has been adapted to learn linguistic knowledge from the Wall Street Journal Corpus. This adaptation is a novel demonstration that this connectionist parser, and by extension, other similar connectionist models, is able to adapt to more than one syntactic tagging convention; this implies their ability to adapt to the underlying linguistic theories used to annotate these corpora
A Connectionist Model of Spatial Knowledge Acquisition in a Virtual Environment
No full textMLIRUM'03, Second Workshop on Machine Learning, Information Retrieval and User Modelling, at 9th International Conference on User Modelling, June 22nd-26th, Pittsburgh, PA, USAThis paper proposes the use of neural networks as a tool for studying
navigation within virtual worlds. Results indicate that network learned to
predict the next step for a given trajectory, acquiring also basic spatial
knowledge in terms of landmarks and configuration of spatial layout. In
addition, the network built a spatial representation of the virtual world, e.g.
cognitive-like map, which preserves the topology but lacks metric accuracy.
The benefits of this approach and the possibility of extending the methodology
to the study of navigation in Human Computer Interaction are discussed.8.7.2013 SB
Connectionist techniques to approach sustainability modelling
No full textWhen defining a context of sustainability, capturing the complexity of data and extracting as much information as possible are fundamental challenges. Normally, quantitative and qualitative indicators are defined. While the definition and calculation of the former is direct, the latter are
difficult to manage. This document provides tools based on connectionist techniques for
managing complex information combining the use of imprecise and qualitative variables. The application of these tools to evaluate non-numerical sustainability indicators is presented. The results obtained in some first approaches are briefly presented to illustrate the connectionist paradigm
Connectionist techniques to approach sustainability modelling
No full textWhen defining a context of sustainability, capturing the complexity of data and extracting as much information as possible are fundamental challenges. Normally, quantitative and qualitative indicators are defined. While the definition and calculation of the former is direct, the latter are
difficult to manage. This document provides tools based on connectionist techniques for
managing complex information combining the use of imprecise and qualitative variables. The application of these tools to evaluate non-numerical sustainability indicators is presented. The results obtained in some first approaches are briefly presented to illustrate the connectionist paradigm
Breaking the 'Glass Ceiling' of Risk Prediction in Recidivism: An Application of Connectionist Modelling to Offender Data
No full textThe present thesis explored the capability of connectionist models to break through the ‘glass ceiling’ of accuracy currently in operation in recidivism prediction (e.g., Yang, Wong, & Coid, 2010). Regardless of the inclusion of dynamic items, all risk measures rarely exceed .75 in terms of the area under the receiver operating characteristic curve (AUC) (Hanley & McNeil, 1982). This may reflect the emphasis of multiple regression equations on main effects of a few key variables tapping long-term anti-social potential. Connectionist models, not used in criminal justice, represent a promising alternative means of combining predictors given their ability to model interactions automatically. To promote learning from other fields a systematic review of the literature on the application of connectionist models to operational data is presented. Lessons were then taken forward in the development of a connectionist model suitable for the present data which comprised fields from the Offender Assessment System (OASys) (Home Office, 2002) relating to 4,048 offenders subject to probation supervision. Included in the items for modelling was the Offender Group Reconviction Scale (OGRS) (Copas & Marshall, 1998; Taylor, 1999). Combining static and dynamic items using conventional statistical methods showed a maximum cross-validated AUC of .82. Using the connectionist model however a substantial increase in accuracy was observed, AUC=.98, and this largely maintained when variations in time to recidivism were controlled. Variation to model parameters suggested that performance linked to the resources in the middle layer, responsible for modelling rare patterns and interactions between items. Model pruning confirmed that while the connectionist model exploited a wide range of variables in its classification decisions, the linear model was affected mainly by OGRS and a limited number of other variables. Results are discussed in terms of the theoretical and practical benefits of developing the use of connectionist models for better incorporating individuals’ dynamic risk and protective factors in recidivism assessments, and reducing the costs associated with false classifications
Modelling individual variability in cognitive development
No full textInvestigating variability in reasoning tasks can provide insights into key issues in the study of cognitive development. These include the mechanisms that underlie developmental transitions, and the distinction between individual differences and developmental disorders. We explored the mechanistic basis of variability in two connectionist models of cognitive development, a model of the Piagetian balance scale task (McClelland, 1989) and a model of the Piagetian conservation task (Shultz, 1998). For the balance scale task, we began with a simple feed-forward connectionist model and training patterns based on McClelland (1989). We investigated computational parameters, problem encodings, and training environments that contributed to variability in development, both across groups and within individuals. We report on the parameters that affect the complexity of reasoning and the nature of ‘rule’ transitions exhibited by networks learning to reason about balance scale problems. For the conservation task, we took the task structure and problem encoding of Shultz (1998) as our base model. We examined the computational parameters, problem encodings, and training environments that contributed to variability in development, in particular examining the parameters that affected the emergence of abstraction. We relate the findings to existing cognitive theories on the causes of individual differences in development
Metaphor as categorisation: a connectionist implementation
No full textA key issue for models of metaphor comprehension is to explain how in some metaphorical comparison , only some features of B are transferred to A. The features of B that are transferred to A depend both on A and on B. This is the central thrust of Black's well known interaction theory of metaphor comprehension (1979). However, this theory is somewhat abstract, and it is not obvious how it may be implemented in terms of mental representations and processes. In this paper we describe a simple computational model of on-line metaphor comprehension which combines Black's interaction theory with the idea that metaphor comprehension is a type of categorisation process (Glucksberg & Keysar, 1990, 1993). The model is based on a distributed connectionist network depicting semantic memory (McClelland & Rumelhart, 1986). The network learns feature-based information about various concepts. A metaphor is comprehended by applying a representation of the first term A to the network storing knowledge of the second term B, in an attempt to categorise it as an exemplar of B. The output of this network is a representation of A transformed by the knowledge of B. We explain how this process embodies an interaction of knowledge between the two terms of the metaphor, how it accords with the contemporary theory of metaphor stating that comprehension for literal and metaphorical comparisons is carried out by identical mechanisms (Gibbs, 1994), and how it accounts for both existing empirical evidence (Glucksberg, McGlone, & Manfredi, 1997) and generates new predictions. In this model, the distinction between literal and metaphorical language is one of degree, not of kind
Connectionist Inference Models
No full textThe performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rule-based reasoning, and whether they involve distributed or localist representations. The benefits and disadvantages of different representations and systems are outlined, and conclusions drawn regarding the capabilities of connectionist inference systems when compared with symbolic inference systems or when used for cognitive modeling
Are developmental disorders like cases of adult brain damage? Implications from connectionist modelling
No full textIt is often assumed that similar domain-specific behavioural impairments found in cases of adult brain damage and developmental disorders correspond to similar underlying causes, and can serve as convergent evidence for the modular structure of the normal adult cognitive system. We argue that this correspondence is contingent on an unsupported assumption that atypical development can produce selective deficits while the rest of the system develops normally (Residual Normality), and that this assumption tends to bias data collection in the field. Based on a review of connectionist models of acquired and developmental disorders in the domains of reading and past tense, as well as on new simulations, we explore the computational viability of Residual Normality and the potential role of development in producing behavioural deficits. Simulations demonstrate that damage to a developmental model can produce very different effects depending on whether it occurs prior to or following the training process. Because developmental disorders typically involve damage prior to learning, we conclude that the developmental process is a key component of the explanation of endstate impairments in such disorders. Further simulations demonstrate that in simple connectionist learning systems, the assumption of Residual Normality is undermined by processes of compensation or alteration elsewhere in the system. We outline the precise computational conditions required for Residual Normality to hold in development, and suggest that in many cases it is an unlikely hypothesis. We conclude that in developmental disorders, inferences from behavioural deficits to underlying structure crucially depend on developmental conditions, and that the process of ontogenetic development cannot be ignored in constructing models of developmental disorders
- …
