Lexical Semantics and Knowledge Representation in Multilingual Text GenerationIn 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. |
Contents
LEXICALIZATION IN | 9 |
CLASSIFYING LEXICAL VARIATION | 33 |
MODELLING THE DOMAIN | 43 |
SITSPEC AND SEMSPEC | 71 |
Connotation | 90 |
4 | 113 |
VERB ALTERNATIONS AND EXTENSIONS | 121 |
A SYSTEM ARCHITECTURE FOR MULTILINGUAL GENERATION | 141 |
GENERATING PARAPHRASES | 163 |
FROM SENTENCES TO TEXT | 181 |
SUMMARY AND CONCLUSIONS | 193 |
209 | |
217 | |
Other editions - View all
Lexical Semantics and Knowledge Representation in Multilingual Text Generation Manfred Stede No preview available - 2012 |
Common terms and phrases
ABox actee ACTIVITY actor adverbs Aktionsart alternation apply approach aspects CAUSER Chapter collocations concepts configurations connotations constraints corresponding covered covering-list decisions defconcept defined denotation directed-action lex disconnected discourse markers distinction domain model drained elements encoded English entities event example expressed extension rules Figure fill-state filled the tank fillers fine-grained foreground German goals grammar input instance interlingua Jill knowledge base knowledge representation language-specific lexemes lexical choice lexical entries lexical items lexical semantics lexicon linguistic linking LOCATION-STATE LOOM mapping matching MOOSE multilingual natural language nondirected-action nouns object ontology paraphrases partial SemSpec PATH PENMAN phrasal phrase possible POST-STATE PRE-STATE preferred produce range relations representation result role salience Section sentence SitSpec node situation specific structure stylistic subsumption synonymy syntactic target language task taxonomy TBox tion UM-type UNITRAN Upper Model utterance variables verb verbalization options word meaning
References to this book
The Description Logic Handbook: Theory, Implementation and Applications Franz Baader No preview available - 2003 |