+612 9045 4394
 
CHECKOUT
Lexical Semantics and Knowledge Representation in Multilingual Text Generation : KLUWER INTERNATIONAL SERIES IN ENGINEERING AND COMPUTER SCIENCE - Manfred Stede

Lexical Semantics and Knowledge Representation in Multilingual Text Generation

KLUWER INTERNATIONAL SERIES IN ENGINEERING AND COMPUTER SCIENCE

Hardcover

Published: 31st January 1999
Ships: 7 to 10 business days
7 to 10 business days
RRP $743.99
$515.25
31%
OFF
or 4 easy payments of $128.81 with Learn more

Other Available Formats (Hide)

  • Paperback View Product Published: 23rd October 2012
    $316.20

In knowledge-based natural language generation, issues of formal knowledge representation meet with the linguistic problems of choosing the most appropriate verbalization in a particular situation of utterance. Lexical Semantics and Knowledge Representation in Multilingual Text Generation presents a new approach to systematically linking the realms of lexical semantics and knowledge represented in a description logic. For language generation from such abstract representations, lexicalization is taken as the central step: when choosing words that cover the various parts of the content representation, the principal decisions on conveying the intended meaning are made. A preference mechanism is used to construct the utterance that is best tailored to parameters representing the context.
Lexical Semantics and Knowledge Representation in Multilingual Text Generation develops the means for systematically deriving a set of paraphrases from the same underlying representation with the emphasis on events and verb meaning. Furthermore, the same mapping mechanism is used to achieve multilingual generation: English and German output are produced in parallel, on the basis of an adequate division between language-neutral and language-specific (lexical and grammatical) knowledge.
Lexical Semantics and Knowledge Representation in Multilingual Text Generation provides detailed insights into designing the representations and organizing the generation process. Readers with a background in artificial intelligence, cognitive science, knowledge representation, linguistics, or natural language processing will find a model of language production that can be adapted to a variety of purposes.

`I recommend the book not only to researchers interested in text generation and in machine translation, but to everybody interested in the relationship between language-independent knowledge representation and language-specific ontologies... Stede's specific proposal is well defined and effective.' Computational Linguistics, 26:2

List of Figuresp. vii
List of Tablesp. ix
Prefacep. xi
Acknowledgmentsp. xv
Introductionp. 1
Natural language generationp. 1
Goals of this researchp. 4
Overview of the bookp. 6
Lexicalization in NLGp. 9
Introductionp. 9
The nature of lexical items in NLPp. 10
Linking concepts to lexical itemsp. 12
Criteria for lexical choicep. 19
Placing lexicalization in the generation processp. 25
Conclusions: making progress on lexicalizationp. 27
Classifying Lexical Variationp. 33
Intra-lingual paraphrasesp. 33
Inter-lingual divergencesp. 37
Divergences as paraphrasesp. 40
Modelling the Domainp. 43
Building domain models for NLGp. 43
Knowledge representation in LOOMp. 45
Ontological categoriesp. 47
The domain modelp. 56
Levels of Representation: Sitspec and Semspecp. 65
Finding appropriate representation levels in NLGp. 65
Linguistic ontology: adapting the 'Upper Model'p. 71
SitSpecsp. 77
SemSpecsp. 80
Representing the Meaning of Wordsp. 85
Introduction: Lexical semanticsp. 85
Denotation and coveringp. 96
Partial SemSpecsp. 102
Connotationp. 110
Saliencep. 113
Verb Alternations and Extensionsp. 121
Background: verb alternationsp. 121
Alternations as meaning extensionsp. 123
Lexical rules for alternations and extensionsp. 125
Extension rules for circumstancesp. 131
Examples: lexical entries for verbsp. 135
Summaryp. 136
A System Architecture for Multilingual Generationp. 141
Lexicalization with constraints and preferencesp. 141
The computational problemp. 144
Architecture and algorithmp. 146
Implementation: MOOSEp. 157
Summary: lexicalization qua subsumptionp. 161
Generating Paraphrasesp. 163
Verbalizing statesp. 163
Verbalizing activitiesp. 167
Verbalizing eventsp. 169
Solutions to lexicalization problemsp. 176
From Sentences to Textp. 181
Text representationp. 181
Embedding MOOSE in a text generatorp. 188
Example: technical documentationp. 191
Summary and Conclusionsp. 193
Summary of the workp. 193
Comparison to related workp. 197
Directions for future researchp. 206
Referencesp. 209
Indexp. 217
Table of Contents provided by Syndetics. All Rights Reserved.

ISBN: 9780792384199
ISBN-10: 0792384199
Series: KLUWER INTERNATIONAL SERIES IN ENGINEERING AND COMPUTER SCIENCE
Audience: Professional
Format: Hardcover
Language: English
Number Of Pages: 219
Published: 31st January 1999
Publisher: Springer
Country of Publication: NL
Dimensions (cm): 24.13 x 15.88  x 1.91
Weight (kg): 0.52