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

By Jill Fain Lehman

As the pc steadily automates human-oriented initiatives in a number of environ­ ments, the interface among pcs and the ever-wider inhabitants of human clients assumes steadily expanding significance. within the workplace atmosphere, for example, clerical projects corresponding to record submitting and retrieval, and higher-level initiatives similar to scheduling conferences, making plans journey itineraries, and generating files for booklet, are being in part or completely automatic. the diversity of clients for place of work­ orientated software program comprises clerks, secretaries, and businesspersons, none of whom are predominantly laptop literate. an identical phenomenon is echoed within the manufacturing unit creation line, within the securities buying and selling flooring, in govt enterprises, in educa­ tional associations, or even in the house. The arcane command languages of certain­ teryear have confirmed too excessive a barrier for soft popularity of automated func­ tions into the office, regardless of how priceless those services might be. machine­ naive clients easily don't take some time to benefit intimidating and complicated laptop interfaces. that allows you to position the performance of modem desktops on the disposition of numerous person populations, a couple of various techniques were attempted, many assembly with an important degree of luck, to wit: specific 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 so much in actual fact within the Apple Macintosh), and interacting with the person in his or her language of choice.

Show description

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

Similar intelligence & semantics books

GWAI-92: Advances in Artificial Intelligence: 16th German Conference on Artificial Intelligence, Bonn, Germany, August 31 - September 3, 1992. Proceedings ...

This quantity offers the complaints of the 16th German convention on synthetic Intelligence, held within the Gustav Stresemann Institute in Berlin from August 31 to September three, 1992. the quantity comprises 24 papers presentedin the technical classes, eight papers chosen from the workshop contributions, and an invited speak via D.

Advances in Technological Applications of Logical and Intelligent Systems: Selected Papers from the Sixth Congress on Logic Applied to Technology

Within the 20th century, good judgment ultimately came upon a few vital purposes and diverse new components of study originated then, particularly after the improvement of computing and the development of the correlated domain names of data (artificial intelligence, robotics, automata, logical programming, hyper-computation, and so on.

Support Vector Machines and Evolutionary Algorithms for Classification: Single or Together?

While discussing class, aid vector machines are identified to be a able and effective strategy to research and expect with excessive accuracy inside a short time-frame. but, their black field potential to take action make the sensible clients really circumspect approximately counting on it, with out a lot figuring out of the how and why of its predictions.

Behavioral Program Synthesis with Genetic Programming

Genetic programming (GP) is a well-liked heuristic technique of application synthesis with origins in evolutionary computation. during this generate-and-test procedure, candidate courses are iteratively produced and evaluated. The latter includes working courses on assessments, the place they convey complicated behaviors mirrored in adjustments of variables, registers, or reminiscence.

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

Example text

When the Parse/Recovery Cycle produces more than one annotated parse tree (APT) we consider the set of APTs as competing explanations of the utterance. Resolution (Chapter 7) is responsible for selecting the intended meaning from this set and performing the user's requested action. To accomplish resolution CHAMP may require guidance from the user, or may need nothing more than the additional constraints provided by the entries in the databases. Once a meaning has been assigned to a deviant utterance, the system is ready to adapt the grammar so that the previously unknown form can be recognized directly in the future as a way of referring to the semantic structure.

We can satisfy the first two conditions by demonstrating that the Regularity and Deviation Hypotheses are true. 3, state that with frequent interaction a user will develop, and come to rely on, idiosyncratic language patterns: Hl. The Regularity Hypothesis: In a natural language interface used by the same individual over time, the user tends to rely on those forms of expression that she remembers as having worked in the past. In other words, we assume that frequent use leads the user to a stylized and self-bounded grammar.

As a result, task times increase as the new forms are learned. When these forms stabilize, response times fall to new lows because the shorter forms take less time to check against the grammar. User 6 shows the same general trend in time spent as those in the adaptive conditions both because her initial grammar conformed so closely to the kernel and because she is consistent in her use of what worked in the past User 8 shows neither consistent decline in the time taken each session nor in the number of uninterpretable sentences (see Figure 3-5).

Download PDF sample

Rated 4.10 of 5 – based on 17 votes