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.
@InProceedings{ARCAN18.541, author = {Mihael Arcan and Elena Montiel-Ponsoda and John Philip McCrae and Paul Buitelaar}, title = "{Automatic Enrichment of Terminological Resources: the IATE RDF Example}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, language = {english} }
Summary of the paper