Lexical semantics and knowledge representation in multilingual text generation / by Manfred Stede.

Format:

Book

Author/Creator:

Stede, Manfred, 1965-

Contributor:

Sabin W. Colton, Jr., Memorial Fund.

Series:

Kluwer international series in engineering and computer science

The Kluwer international series in engineering and computer science

Language:

English

Subjects (All):

Computational linguistics.

Semantics--Data processing.

Semantics.

Knowledge representation (Information theory).

Physical Description:

xiii, 219 pages : illustrations ; 24 cm.

Place of Publication:

Boston ; London : Kluwer Academic, [1999]

Summary:

This book 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.

Contents:

1.1 Natural language generation 1

1.2 Goals of this research 4

1.3 Overview of the book 6

2. Lexicalization in NLG 9

2.2 The nature of lexical items in NLP 10

2.3 Linking concepts to lexical items 12

2.4 Criteria for lexical choice 19

2.5 Placing lexicalization in the generation process 25

2.6 Conclusions: making progress on lexicalization 27

3. Classifying Lexical Variation 33

3.1 Intra-lingual paraphrases 33

3.2 Inter-lingual divergences 37

3.3 Divergences as paraphrases 40

4. Modelling the Domain 43

4.1 Building domain models for NLG 43

4.2 Knowledge representation in LOOM 45

4.3 Ontological categories 47

4.4 The domain model 56

5. Levels of Representation: Sitspec and Semspec 65

5.1 Finding appropriate representation levels in NLG 65

5.2 Linguistic ontology: adapting the 'Upper Model' 71

5.3 SitSpecs 77

5.4 SemSpecs 80

6. Representing the Meaning of Words 85

6.1 Introduction: Lexical semantics 85

6.2 Denotation and covering 96

6.3 Partial SemSpecs 102

6.4 Connotation 110

6.5 Salience 113

7. Verb Alternations and Extensions 121

7.1 Background: verb alternations 121

7.2 Alternations as meaning extensions 123

7.3 Lexical rules for alternations and extensions 125

7.4 Extension rules for circumstances 131

7.5 Examples: lexical entries for verbs 135

8. A System Architecture for Multilingual Generation 141

8.1 Lexicalization with constraints and preferences 141

8.2 The computational problem 144

8.3 Architecture and algorithm 146

8.4 Implementation: MOOSE 157

8.5 Summary: lexicalization qua subsumption 161

9. Generating Paraphrases 163

9.1 Verbalizing states 163

9.2 Verbalizing activities 167

9.3 Verbalizing events 169

9.4 Solutions to lexicalization problems 176

10. From Sentences to Text 181

10.1 Text representation 181

10.2 Embedding MOOSE in a text generator 188

10.3 Example: technical documentation 191

11.1 Summary of the work 193

11.2 Comparison to related work 197

11.3 Directions for future research 206.

Notes:

Includes bibliographical references (pages [209]-216) and index.

Local Notes:

Acquired for the Penn Libraries with assistance from the Sabin W. Colton, Jr., Memorial Fund.

ISBN:

0792384199

OCLC:

40397135