Search Results

Chapter 4 discusses how the immediacy of language processing provides a fundamental constraint on theories of language acquisition and evolution. Language happens in the here-and-now. Because memory is fleeting, new material will rapidly obliterate previous material, creating a Now-or-Never bottleneck. To successfully deal with the continual deluge of linguistic information, the brain must compress and recode its input into “chunks” as rapidly as possible. It must deploy all available information predictively to ensure that local linguistic ambiguities are dealt with Right-First-Time; once the original input is lost, there is no way to recover it. Similarly, language learning must also occur in the here-and-now. This implies that language acquisition involves learning how to process linguistic structure, rather than inducing a grammar. Incoming language is recoded incrementally into chunks of increasing granularity, from sounds to constructions, and beyond. Importantly, several key properties of language follow naturally from this perspective, including the local nature of linguistic dependencies, the quasi-regular nature of linguistic structure, multiple levels of linguistic representation, and duality of patterning (i.e., that meaningful units are composed of smaller elements).

The most sophisticated and efficient means of communication between humans is spoken natural language (NL). It is a rare circumstance when two people choose to communicate via another means when spoken natural language is possible. Ochsman and Chapanis [OC74] conducted a study involving two person teams solving various problems using restricted means of communication such as typewriting and video, typewriting only, handwriting and video, voice and video, voice only, etc. Their conclusion included the following statement. . . . The single most important decision in the design of a telecommunications link should center around the inclusion of a voice channel. In the solution of factual real-world problems, little else seems to make a demonstrable difference . . . Thus, it would seem desirable to develop computer systems that can also communicate with humans via spoken natural language dialog. Furthermore, recent reports from the research community in speech recognition [Adv93] indicate that accuracy levels in speaker-independent continuous speech recognition have reached a threshold where practical applications of spoken natural language are viable. This book addresses the dialog issues that must be resolved in building effective spoken natural language dialog systems—systems where both the human and computer interact via spoken natural language. We present an architecture for dialog processing for which an implementation in the equipment repair domain has been constructed that exhibits a number of behaviors required for efficient human-machine dialog. These behaviors include the following. • Problem solving to achieve a target goal. • The ability to carry out subdialogs to achieve appropriate subgoals and to pass control arbitrarily from one subdialog to another. • The use of a user model to enable useful verbal exchanges and to inhibit unnecessary ones. • The ability to use context dependent expectations to correct speech recognition and track user movement to new subdialogs. • The ability to vary the task/dialog initiative from strongly computer controlled to strongly user controlled or somewhere in between.