Translating the FINREP taxonomy using a domain-specific corpus
Arcan, Mihael Thomas, Susan Marie De Brandt, Derek Buitelaar, Paul
Arcan, Mihael
Thomas, Susan Marie
De Brandt, Derek
Buitelaar, Paul
Loading...
Repository DOI
Publication Date
2013-09-02
Keywords
Type
Conference Paper
Downloads
Citation
Arcan, Mihael, Thomas, Susan Marie, De Brandt, Derek, & Buitelaar, Paul. (2013). Translating the FINREP taxonomy using a domain-specific corpus. Paper presented at the 14th Machine Translation Summit XIV, Nice, France, 02-0 6 September.
Abstract
Our research investigates the use of statistical machine translation (SMT) to translate the labels of concepts in an XBRL taxonomy. Often taxonomy concepts are given labels in only one language. To enable knowledge access across languages, such monolingual taxonomies need to be translated into other languages. The primary challenge in label translation is the highly domain-specific vocabulary. To meet this challenge we adopted an approach based on the creation of domainspecific resources. Application of this approach to the translation of the FINREP taxonomy, translating from English to German, showed that it significantly outperforms SMT trained on general resources.
Publisher
IAMT and EAMT
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland