Extraction of Multilingual Term Variants in the Business Reporting Domain

Thierry Declerck, Dagmar Gromann

Publication: Chapter in book/Conference proceedingContribution to conference proceedings

Abstract

Within the context of the European research project "Monnet",
which implements among other activities ontology-based multilingual
information extraction, we tackle the the issue of recognizing variants
of concept labels in business reports that guide the information
extraction process. In this short paper, we describe two related experiments
in finding variants of multilingual taxonomy labels used in business
reporting - across distinct reporting legislations and languages. A
core taxonomy developed by the XBRL-Europe Association provides a
starting point, as we map multilingual term variant candidates we extract from the web presence of relevant players in the field of business reporting to its labels.
Original languageEnglish
Title of host publicationProceedings of CHAT 2012: The 2nd Workshop on the Creation, Harmonization and Application of Terminology Resources. Workshop on the Creation, Harmonization and Application of Terminology Resources (CHAT-12)
Editors Tatiana Gornostay
Place of PublicationMadrid
Pages41 - 47
Publication statusPublished - 1 Nov 2012

Cite this