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 desktops and the ever-wider inhabitants of human clients assumes gradually expanding significance. within the workplace atmosphere, for example, clerical projects comparable to record submitting and retrieval, and higher-level projects comparable to scheduling conferences, making plans journey itineraries, and generating files for e-book, are being in part or completely computerized. the diversity of clients for place of work­ orientated software program comprises clerks, secretaries, and businesspersons, none of whom are predominantly desktop literate. an identical phenomenon is echoed within the manufacturing facility creation line, within the securities buying and selling flooring, in govt businesses, in educa­ tional associations, or even in the house. The arcane command languages of definite­ teryear have confirmed too excessive a barrier for tender popularity of automated func­ tions into the place of work, irrespective of how valuable those capabilities should be. desktop­ naive clients easily don't make the effort to benefit intimidating and intricate machine interfaces. so as to position the performance of modem pcs on the disposition of numerous person populations, a couple of varied ways were attempted, many assembly with an important degree of good fortune, to wit: targeted classes to coach clients within the less complicated command languages (such as MS-DOS), designing point-and-click menu/graphics interfaces that require less consumer familiarization (illustrated so much essentially 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

Handbook of Knowledge Representation

Wisdom illustration, which lies on the center of synthetic Intelligence, is anxious with encoding wisdom on pcs to let platforms to cause immediately. The guide of data illustration is an updated evaluation of twenty-five key subject matters in wisdom illustration, written by way of the leaders of every box.

Semantic Web Technologies for e-Learning, The Future of Learning, Volume 4

This ebook outlines the newest examine, theoretical and technological advances, and purposes of semantic internet and internet 2. zero applied sciences in e-learning. It offers a consultant for researchers and builders to the current and destiny developments of analysis during this box. The ebook, incorporating a few papers from the foreign Workshop on Ontologies and Semantic net in e-Learning (SWEL), is split into 3 sections.

Singular Perturbation Methods for Ordinary Differential Equations

This booklet effects from a variety of lectures given in recent times. Early drafts have been used for a number of unmarried semester classes on singular perturbation meth­ ods given at Rensselaer, and a extra whole model used to be used for a 12 months direction on the Technische Universitat Wien. a few parts were used for brief lecture sequence at Universidad important de Venezuela, West Vir­ ginia college, the collage of Southern California, the collage of California at Davis, East China basic collage, the college of Texas at Arlington, Universita di Padova, and the collage of latest Hampshire, between different locations.

Symbolic dynamics : one-sided, two-sided, and countable state Markov shifts

Approximately 100 years in the past Jacques Hadamard used countless sequences of symbols to investigate the distribution of geodesics on yes surfaces. That was once the start of symbolic dynamics. within the 1930's and 40's Arnold Hedlund and Marston Morse back used countless sequences to enquire geodesics on surfaces of unfavourable curvature.

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

Example text

In order to expand the vocabulary, the system had to be returned to Phase I; similarly, to extend the grammar, it had to be returned to Phase II. 4). At the discourse level we find the recent work of Fink and Biermann, VLNCE [19], which notices and remembers regularities in interface behavior in order to help predict future actions. In contrast to our work, VLNCE tracks dialogue expectations in order to predict lexical items to correct for speech recognition failures. The system builds a behavior graph in which the nodes correspond to the meaning structures of utterances it has encountered-no record of the structure of the utterances themselves is kept.

Since new instances of known classes are exactly the sort of change that continues to occur even after the grammar has stabilized, we want to make learning them relatively inexpensive and routine. In the algorithm above, learning new class instances is accomplished at Deviation-level O. Another point of interest is the limit of two deviations in a learnable utterance in Rule 3. The model presented in Chapter 2 has no inherent limit; search continues in a least-deviant-frrst manner until a verified interpretation is found.

0 C'l ..... ..... Ir'l c::t ........ ........ ..... :t ..... Ir'l ('<") 1 2 ('<") ('<") 3 4 5 Figure 3·4: Self·limiting behavior in the Adapt/Echo condition measured by number of new constructions/number of interpretable sentences. Reprinted with permission of Springer-Verlag experience did, however, conform well with a broader interpretation of Slator's claims and replicated the experiences of Good et al. [24] and Cobourn [14]: there is a strong assumption on the part of users that whatever the system can generate it can also parse.

Download PDF sample

Rated 4.56 of 5 – based on 38 votes