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

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 significance. within the workplace surroundings, for example, clerical projects akin to rfile submitting and retrieval, and higher-level projects corresponding to scheduling conferences, making plans journey itineraries, and generating records for e-book, are being partly or absolutely computerized. the variety of clients for place of work­ orientated software program contains clerks, secretaries, and businesspersons, none of whom are predominantly machine literate. an analogous phenomenon is echoed within the manufacturing unit creation line, within the securities buying and selling flooring, in executive companies, in educa­ tional associations, or even in the house. The arcane command languages of convinced­ teryear have confirmed too excessive a barrier for gentle attractiveness of automatic func­ tions into the place of work, irrespective of how necessary those services can be. desktop­ naive clients easily don't make the effort to profit intimidating and intricate machine interfaces. in an effort to position the performance of modem desktops on the disposition of numerous consumer populations, a couple of diverse techniques were attempted, many assembly with an important degree of luck, to wit: particular classes to coach clients within the easier command languages (such as MS-DOS), designing point-and-click menu/graphics interfaces that require less person familiarization (illustrated so much in actual fact 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

Information Modelling and Knowledge Bases XIX

Within the final a long time details modelling and data bases became sizzling subject matters not just in educational groups relating to info structures and laptop technological know-how, but additionally in enterprise components the place info know-how is utilized. This booklet contains papers submitted to the seventeenth European-Japanese convention on info Modelling and information Bases (EJC 2007).

Indistinguishability Operators: Modelling Fuzzy Equalities and Fuzzy Equivalence Relations

Indistinguishability operators are crucial instruments in fuzzy common sense considering the fact that they fuzzify the strategies of equivalence relation and crisp equality. This ebook collects all of the major points of those operators in one quantity for the 1st time. the tension is wear the learn in their constitution and the monograph starts off offering different ways that indistinguishability operators might be generated and represented.

The Turing Test and the Frame Problem: Ai's Mistaken Understanding of Intelligence

Either the Turing attempt and the body challenge were major goods of debate because the Seventies within the philosophy of man-made intelligence (AI) and the philisophy of brain. besides the fact that, there was little attempt in the course of that point to distill how the body challenge bears at the Turing try out. If it proves to not be solvable, then not just will the try out no longer be handed, however it will name into query the belief of classical AI that intelligence is the manipluation of formal constituens lower than the keep watch over of a application.

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

Example text

One must also assume that the task of understanding a user's utterance about her own language is somehow less difficult than understanding a user's utterance about a restricted task domain. Neither assumption seems warranted. 5. Prior research in adaptation Previous work in automatic language acquisition falls broadly into one of two categories: theories of child language learning that try to account for existing developmental data, or fundamentally non-cognitive models that argue for a particular learning mechanism.

Before investing the resources required to implement an adaptive interface, it seemed appropriate to ascertain the validity of those assumptions. To accomplish this, we used a technique that is fairly common in evaluating natural language interface designs-the hidden-operator experiment A hidden-operator experiment is one in which the user believes she is interacting with a computer system, when, in reality, the feedback is produced by an experimenter simulating the system's behavior. To accomplish the simulation the user's typed input is viewed remotely by the experimenter who constructs a response according to the algorithm being simulated (see Figure 3-2).

Although noteworthy for its scope, Siklossy's approach is incompatible in two ways with the constraints imposed on a natural language learning interface. Whereas a learning interface cannot assume grammaticality, ZBIE functioned under the assumption that the utterance was syntactically correct. More importantly, ZBIE was given both a language utterance and a meaning structure as input whereas a learning interface's search for the meaning of an utterance is its fundamental task. Also at the sentential level is work by Harris [28].

Download PDF sample

Rated 4.90 of 5 – based on 33 votes