ISSN:0954-0091    

DOI:10.1080/09540099008915674

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

摘要:

Neural networks which act as state machines are applied to a variety of natural language tasks. Both generation of sequences and recognition are considered. Among the generation tasks are descriptions and planning. The recognition tasks include question answering, pronoun reference, action identification, and analogy completion. Overall, these studies introduce the use of connectionist state machines as intelligent agents in which the emphasis is on perception of and interaction with their environment through language; thus the agents are termed connectionist language users (CLUES).

ISSN:0954-0091    

DOI:10.1080/09540099008915675

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

摘要:

We propose a new method for developing distributed connectionist representations in order to serve as an adequate foundation for constructing and manipulating conceptual knowledge. In our approach, distributed representations of semantic relations (i.e. propositions) are formed by recirculating the hidden layer in two auto-associative recurrent PDP (parallel distributed processing) networks, and our experiments show that the resulting distributed semantic representations (DSRs) have many desirable properties such as automaticity, portability, structure-encoding ability and similarity-based distributed representations. We have constructed a symbolic/connectionist hybrid script-based story processing system DYNASTY (DYNAmic STory understanding sYstem) which incorporates DSR learning and 6 script related processing modules. Each module communicates through a global dictionary, where DSRs are stored, DYNASTY is able to (1) learn similarity-based distributed representations of concepts and events in everyday scriptal experiences, (2) perform script-based causal chain completion inferences according to the acquired sequential knowledge, and (3) perform script role association and retrieval during script application.

ISSN:0954-0091    

DOI:10.1080/09540099008915676

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

摘要:

A single layer higher order dynamic topology neural net called HODYNE is described, targeted at natural language processing problems, HODYNE has an input layer of nodes containing concatenations of words from the input string, and grows nodes during training which are dependent on the training data. The training procedure also has some novel features. Results are presented on the problem of grammaticality determination. The results are encouraging, with almost perfect performance on unseen test sets derived from simple context-free grammars. An important aspect of this work is that the data sets used in training and testing are larger than is common in the research literature.

ISSN:0954-0091    

DOI:10.1080/09540099008915677

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099008915678

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099008915679

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099008915680

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099008915681

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099008915682

出版商:Taylor & Francis Group    

年代:1990

数据来源: Taylor