Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
These are special words and phrases directly indicating the structure of the argument to the hearer. Two main conclusions are drawn: I) clue words can occur in conjunction with coherent transmissions, to reduce processing of the hearer 2) clue words must occur with more complex forms of transmission, to facilitate recognition of the argument structure. Interpretation rules to process clues are proposed. In addition, a relationship between use of clues and complexity of processing is suggested for the case of exceptional transmission strategies. . | CONTROL STRUCTURES AND THEORIES OF INTERACTION IN SPEECH UNDERSTANDING SYSTEMS E.J. Briscoe and B.K. Boguraev University of Cambridge Computer Laboratory Corn Exchange Street Cambridge CB2 3QG England ABSTRACT In this paper we approach the problem of organisation and control in automatic speech understanding systems firstly by presentin a theory of the non-serial interactions necessary between two processors in the system namely the morphosyntact.ic and the prosodic and secondly by showing how when generalised this theory allows one to specify a highly efficient architecture for a speech understanding system with a simple control structure and genuinely independent components. The theory of non-serial interactions we present predicts that speech is temporally organised in a very specific way that is the system would not function effectively if the temporal distribution of various types of information in speech were different. The architecture we propose is developed from a study of the task of speech understanding and furthermore is specific to this task. Consequently the paper argues that general problem solving methods are unnecessary for speech understanding. 1 INTRODUCTION It is generally accepted that the control structures of speech understanding systems SUSs must allow for non-serial interactions between different knowledge sources or components within the system. By nonserial interaction NS1 we refer to communication which extends beyond tire normal serial flow of information entailed by the tasks undertaken by each component. For example the output of the word recognition system will provide the input to morphosyntactic analysis almost by definition however the operation of the morphosyntactic analyser should be constrained on some occasions by prosodic cues soy that her is accented and followed by a pause whilst dog is not in 1 Max gave her dog biscuits. Similarly the output of the morphosyntactic analyser will provide the input to semantic analysis but .
