Lexical Semantics and Knowledge Representation in Multilingual Text Generation

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.

Springer Book Archives

1. Introduction.- 1.1 Natural language generation.- 1.2 Goals of this research.- 1.3 Overview of the book.- 2. Lexicalization in NLG.- 2.1 Introduction.- 2.2 The nature of lexical items in NLP.- 2.3 Linking concepts to lexical items.- 2.4 Criteria for lexical choice.- 2.5 Placing lexicalization in the generation process.- 2.6 Conclusions: making progress on lexicalization.- 3. Classifying Lexical Variation.- 3.1 Intra-lingual paraphrases.- 3.2 Inter-lingual divergences.- 3.3 Divergences as paraphrases.- 4. Modelling the Domain.- 4.1 Building domain models for NLG.- 4.2 Knowledge representation in LOOM.- 4.3 Ontological categories.- 4.4 The domain model.- 5. Levels of Representation: Sitspec and Semspec.- 5.1 Finding appropriate representation levels in NLG.- 5.2 Linguistic ontology: adapting the 'Upper Model'.- 5.3 SitSpecs.- 5.4 SemSpecs.- 6. Representing the Meaning of Words.- 6.1 Introduction: Lexical semantics.- 6.2 Denotation and covering.- 6.3 Partial SemSpecs.- 6.4 Connotation.- 6.5 Salience.- 7. Verb Alternations and Extensions.- 7.1 Background: verb alternations.- 7.2 Alternations as meaning extensions.- 7.3 Lexical rules for alternations and extensions.- 7.4 Extension rules for circumstances.- 7.5 Examples: lexical entries for verbs.- 7.6 Summary.- 8. A System Architecture for Multilingual Generation.- 8.1 Lexicalization with constraints and preferences.- 8.2 The computational problem.- 8.3 Architecture and algorithm.- 8.4 Implementation: MOOSE.- 8.5 Summary: lexicalization qua subsumption.- 9. Generating Paraphrases.- 9.1 Verbalizing states.- 9.2 Verbalizing activities.- 9.3 Verbalizing events.- 9.4 Solutions to legalization problems.- 10. From Sentences to Text.- 10.1 Text representation.- 10.2 Embedding MOOSE in a text generator.- 10.3 Example:technical documentation.- 11. Summary and Conclusions.- 11.1 Summary of the work.- 11.2 Comparison to related work.- 11.3 Directions for future research.- References.