Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Constructing Large Multilingual Proposition Databases

Exner, Peter LU (2016)
Abstract
This thesis explores methods for generating proposition databases in a large-scale and multilingual setting. Our methods are centered on using semantic role labeling for extracting predicate-argument structures, and the subsequent transformation of such structures for knowledge base population and generation. By extending semantic role labeling with entity detection, we demonstrate how predicate-argument structures can be transformed to represent real world concepts and also act as a bridge connecting relational facts in multiple languages.
We introduce a framework, KOSHIK, for large scale extraction of propositions from unstructured text and an annotation model for the incremental addition of annotation layers. In addition, we... (More)
This thesis explores methods for generating proposition databases in a large-scale and multilingual setting. Our methods are centered on using semantic role labeling for extracting predicate-argument structures, and the subsequent transformation of such structures for knowledge base population and generation. By extending semantic role labeling with entity detection, we demonstrate how predicate-argument structures can be transformed to represent real world concepts and also act as a bridge connecting relational facts in multiple languages.
We introduce a framework, KOSHIK, for large scale extraction of propositions from unstructured text and an annotation model for the incremental addition of annotation layers. In addition, we introduce an alignment method based on entities for aligning disparate ontologies and also for generating ontologies for new proposition databases. Using KOSHIK, we perform large-scale natural language processing of the entire English, Swedish, and French editions of Wikipedia. By transforming the structures extracted from Wikipedias, we extend existing knowledge bases in addition to generating new proposition databases. We demonstrate how generated proposition databases in Swedish and French can be used to effectively train semantic role labelers. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Professor Sebastian Pado, Universität Stuttgart, Germany
organization
publishing date
type
Thesis
publication status
published
pages
116 pages
defense location
Lecture hall E:1406, E-building, Ole Römers väg 3, Lund University, Faculty of Engineering
defense date
2016-10-14 13:00:00
ISBN
978-91-7623-954-4
978-91-7623-955-1
language
English
LU publication?
yes
id
4def1d7b-1f45-4a95-9f7c-b2f45cfdb04a
date added to LUP
2016-09-19 11:04:21
date last changed
2021-05-06 08:28:09
@phdthesis{4def1d7b-1f45-4a95-9f7c-b2f45cfdb04a,
  abstract     = {{This thesis explores methods for generating proposition databases in a large-scale and multilingual setting. Our methods are centered on using semantic role labeling for extracting predicate-argument structures, and the subsequent transformation of such structures for knowledge base population and generation. By extending semantic role labeling with entity detection, we demonstrate how predicate-argument structures can be transformed to represent real world concepts and also act as a bridge connecting relational facts in multiple languages.<br/>We introduce a framework, KOSHIK, for large scale extraction of propositions from unstructured text and an annotation model for the incremental addition of annotation layers. In addition, we introduce an alignment method based on entities for aligning disparate ontologies and also for generating ontologies for new proposition databases. Using KOSHIK, we perform large-scale natural language processing of the entire English, Swedish, and French editions of Wikipedia. By transforming the structures extracted from Wikipedias, we extend existing knowledge bases in addition to generating new proposition databases. We demonstrate how generated proposition databases in Swedish and French can be used to effectively train semantic role labelers.}},
  author       = {{Exner, Peter}},
  isbn         = {{978-91-7623-954-4}},
  language     = {{eng}},
  month        = {{10}},
  school       = {{Lund University}},
  title        = {{Constructing Large Multilingual Proposition Databases}},
  year         = {{2016}},
}