Automatic enrichment of terminological resources: the IATE RDF example
Date
2018-05-07Author
Arcan, Mihael
Montiel-Ponsoda, Elena
McCrae, John P.
Buitelaar, Paul
Metadata
Show full item recordUsage
This item's downloads: 267 (view details)
Recommended Citation
Arcan, Mihael, Montiel-Ponsoda, Elena, McCrae, John P., & Buitelaar, Paul. (2018). Automatic Enrichment of Terminological Resources: the IATE RDF Example. Paper presented at the LREC 2018, Eleventh International Conference on Language Resources and Evaluation, Miyazaki, Japan, 7-12 May.
Published Version
Abstract
Terminological resources have proven necessary in many organizations and institutions to ensure communication between experts.
However, the maintenance of these resources is a very time-consuming and expensive process. Therefore, the work described in this
contribution aims to automate the maintenance process of such resources. As an example, we demonstrate enriching the RDF version
of IATE with new terms in the languages for which no translation was available, as well as with domain-disambiguated sentences and
information about usage frequency. This is achieved by relying on machine translation trained on parallel corpora that contains the terms
in question and multilingual word sense disambiguation performed on the context provided by the sentences. Our results show that for
most languages translating the terms within a disambiguated context significantly outperforms the approach with randomly selected
sentences.