Comprehending Text : Achieving Coherence through a Connectionist Architecture

Comprehension is determined by the content of memory. The verbalized concepts reflect the information that is in the focus of attention. Mental models of text must be formed in order to achieve coherence in language understanding. Constructing a mental model requires continual interaction between the text and the reader's linguistic, pragmatic, and world knowledge. In this article, a connectionist framework is proposed for the formation of mental models that occurs during comprehension. A unification and spreading activation model are used to simulate the processes. The system is tested using children's stories. Results attest the validity of the model. Thus, our design contributes to the formation of a durable and functional mental representation of the text information.

[1]  Risto Miikkulainen,et al.  Natural Language Processing With Modular PDP Networks and Distributed Lexicon , 1991, Cogn. Sci..

[2]  Samuel W. K. Chan,et al.  An Epistemological Model in Semantic Cognitive Map , 1994 .

[3]  Michael Halliday,et al.  Cohesion in English , 1976 .

[4]  T. Trabasso,et al.  Causal relatedness and importance of story events , 1985 .

[5]  James Franklin,et al.  A neural network model for acquisition of semantic structures , 1994, Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks.

[6]  R. Freedle.  New directions in discourse processing , 1980 .

[7]  Gregory L. Murphy,et al.  Psychological concepts in a parallel system , 1986 .

[8]  Manuel Carreiras,et al.  Representations and processes in the interpretation of pronouns: new evidence from Spanish and French , 1995 .

[9]  Morton Ann Gernsbacher,et al.  Language Comprehension As Structure Building , 1990 .

[10]  N. Stein,et al.  An Analysis of Story Comprehension in Elementary School Children: A Test of a Schema. , 1975 .

[11]  A. Garnham.  Mental models as representations of text , 1981, Memory & cognition.

[12]  James L. McClelland,et al.  A distributed model of human learning and memory , 1986 .

[13]  Mike Rinck,et al.  Anaphora Resolution and the Focus of Attention in Situation Models , 1995 .

[14]  James Franklin,et al.  A Neurosymbolic Integrated Model for Semantic Ambiguation Resolution , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[15]  Arthur C. Graesser,et al.  Dimensions of situation model construction in narrative comprehension. , 1995 .

[16]  S.W.K. Chan,et al.  Inferences in natural language understanding , 1995, Proceedings of 1995 IEEE International Conference on Fuzzy Systems..

[17]  W. Kintsch,et al.  Strategies of discourse comprehension , 1986 .