tailieunhanh - Báo cáo khoa học: "TEXT UNDERSTANDING WITH MULTIPLE KNOWLEDGE SOURCES: AN EXPERIMENT IN DISTRIBUTED PARSING"

A novel approach to the problem of text understanding is presented, which exploits a distributed processing concept, where knowledge from different sources comes into play in the course of comprehension. In the paper the rationale of advocating such an approach and in following it are discussed. A prototype parser based on an original distributed problem-solving architecture is presented. It encompasses a centralized declarative control module and a collection of decentralized, loosely coupled, heterogeneous problem solvers specialized in the vadous facets of the parsing task. . | TEXT UNDERSTANDING WITH MULTIPLE KNOWLEDGE SOURCES AN EXPERIMENT IN DISTRIBUTED PARSING Cinzia Costantini Danilo Fum Giovanni Guida Angelo Montanari Cado Tasso Laboratorio di Intelligenza Artificiale Dipartimento di Matematica e Informatica Universita di Udine Udine Italy ABSTRACT A novel approach to the problem of text understanding is presented which exploits a distributed processing concept where knowledge from different sources comes into play in the course of comprehension. In the paper the rationale of advocating such an approach and the advantages in following it are discussed. A prototype parser based on an original distributed problem-solving architecture is presented. It encompasses a centralized declarative control module and a collection of decentralized loosely coupled heterogeneous problem solvers specialized in the various facets of the parsing task. The mechanisms of coordination and communication among the specialists are illustrated and an example of the parser operation is given. The parser is implemented in LISP on a SUN workstation. 1. INTRODUCTION The processes underlying text understanding involve a variety of complex multifaceted activities which have not been yet completely understood from the cognitive point of view and which still lack adequate computational models. Recent research trends in cognitive science and artificial intelligence however have put forward some ideas concerning human cognition and automatic problem solving that offer promising tools for the design of text understanding systems. One of the key ideas emerged in the field of cognitive study of natural language comprehension is that text understanding constitutes in humans an interactive process where bottom-up data-driven activities combine with top-down expectation-driven ones to cooperatively determine the most likely interpretation of the input Lesgold and Perfetti 1981 . Roughly speaking humans begin with a set of expectations about what information is likely to be