To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Multilingual text generat… - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Multilingual text generation from structured formal representations.

Doctoral thesis
Authors Dana Dannélls
Opponent at public defense Michael Elhadad
ISBN 978-91-87850-48-6
Publisher University of Gothenburg
Place of publication Göteborg
Publication year 2012
Published at Department of Swedish
Language en
Links https://gupea.ub.gu.se/handle/2077/...
Keywords Coherence, computational linguistics, coreference, corpus linguistics discourse structure, knowledge representation, language technology, lexical semantics, linked open data, multilingual natural language generation, natural language processing, ontology, semantic web.
Subject categories Language Technology (Computational Linguistics)

Abstract

This thesis aims to identify the optimal ways in which natural language generation techniques can be brought to bear upon the problem of processing a structured body of information in order to devise a coherent presentation of text content in multiple languages. We investigate how chains of referential expressions are realized in English, Swedish and Hebrew, and suggest several coreference strategies that can be used to generate coherent descriptions about paintings. The suggested strategies focus on the need to produce paragraph-sized written natural language descriptions from formal structured representations presented in the Semantic Web. We account for principles of coreference by introducing a new modularized approach to automatically generate chains of referential expressions from ontologies. We demonstrate the feasibility of the approach by implementing a system where a Semantic Web domain ontology serves as the background knowledge representation and where the language-specific coreference strategies are incorporated. The system uses both the principles of discourse structures and coreference strategies to guide the generation process. We show how the system successfully generates coherent, well-formed descriptions in multiple languages.

Page Manager: Webmaster|Last update: 9/11/2012
Share:

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?