Download Adaptive Parsing: Self-Extending Natural Language Interfaces by Jill Fain Lehman PDF

By Jill Fain Lehman

As the pc progressively automates human-oriented projects in a number of environ­ ments, the interface among pcs and the ever-wider inhabitants of human clients assumes steadily expanding value. within the workplace surroundings, for example, clerical projects resembling record submitting and retrieval, and higher-level projects similar to scheduling conferences, making plans journey itineraries, and generating records for book, are being partly or absolutely computerized. the diversity of clients for workplace­ orientated software program contains clerks, secretaries, and businesspersons, none of whom are predominantly desktop literate. an analogous phenomenon is echoed within the manufacturing unit creation line, within the securities buying and selling flooring, in executive enterprises, in educa­ tional associations, or even in the house. The arcane command languages of sure­ teryear have confirmed too excessive a barrier for delicate recognition of automated func­ tions into the place of work, irrespective of how priceless those features will be. desktop­ naive clients easily don't make the effort to profit intimidating and intricate laptop interfaces. in an effort to position the performance of modem desktops on the disposition of various consumer populations, a couple of varied methods were attempted, many assembly with an important degree of good fortune, to wit: unique classes to coach clients within the easier command languages (such as MS-DOS), designing point-and-click menu/graphics interfaces that require less consumer familiarization (illustrated such a lot basically within the Apple Macintosh), and interacting with the consumer in his or her language of choice.

Show description

Read or Download Adaptive Parsing: Self-Extending Natural Language Interfaces PDF

Similar intelligence & semantics books

Advances in Image Processing and Understanding: A Festschrift for Thomas S. Huang

This quantity of unique papers has been assembled to honour the achievements of Professor Thomas S. Huang within the region of picture processing and picture research. Professor Huang's lifetime of inquiry has spanned a few a long time, as his paintings on imaging difficulties all started in 1960's. through the years, he has made many basic and pioneering contributions to almost each region of this box.

Abductive Inference Models for Diagnostic Problem-Solving

Creating a prognosis while anything is going unsuitable with a typical or m- made procedure could be tough. in lots of fields, comparable to drugs or electr- ics, a protracted education interval and apprenticeship are required to develop into a talented diagnostician. in this time a beginner diagnostician is requested to assimilate a large number of wisdom in regards to the classification of platforms to be clinically determined.

Autonomy Requirements Engineering for Space Missions

Complex area exploration is played by means of unmanned missions with built-in autonomy in either flight and flooring structures. hazard and feasibility are significant components assisting using unmanned craft and using automation and robot applied sciences the place attainable. Autonomy in area is helping to extend the quantity of technological know-how information lower back from missions, practice new technology, and decrease challenge expenses.

Behavioral Program Synthesis with Genetic Programming

Genetic programming (GP) is a well-liked heuristic method of application synthesis with origins in evolutionary computation. during this generate-and-test strategy, candidate courses are iteratively produced and evaluated. The latter contains operating courses on exams, the place they express complicated behaviors mirrored in alterations of variables, registers, or reminiscence.

Extra resources for Adaptive Parsing: Self-Extending Natural Language Interfaces

Sample text

Reprinted with permission of Springer-Verlag had worked in the past, taken as a whole her performance must be seen as a strong counterargument to the notion that everyone finds it natural or easy to adapt to a system's linguistic limitations. The purpose of the experiments described in this chapter was to establish certain behavioral characteristics of frequent users which, in turn, guarantee the conditions necessary for an adaptive interface to benefit user performance. The behavior of the users in the adaptive conditions demonstrates the self-limiting, idiosyncratic language use predicted by the Regularity and Deviation Hypotheses.

Although not advanced as a psychological model of child language acquisition, Harris's intent was to teach his robot natural language under the same conditions children learn it. By breaking acquisition down into distinct phases, he built a system able to learn both word meanings and sentential forms. In Phase I, the system received utterance-action description pairs and learned the meaning of individual words by building a correlation table. In Phase II, a kind of context-free-grammar was induced from a fixed set of sentences composed from the vocabulary learned in Phase I.

A change was considered complex if there were a number of ways it could be integrated into the grammar; between sessions, one new form was chosen. Sentences that were learnable by constructive inference (Rule 4) were almost always complex in this sense because the model does not specify a method of generalization. Although we discuss this (and other) problems of underspecification in Chapter 9, we note here that the delayed adaptations for com- 34 User Behavior in an Adaptive Environment plex forms did not seem to effect materially those aspects of performance we were examining.

Download PDF sample

Rated 4.71 of 5 – based on 44 votes