From Linguistic Resources to Ontology-Aware Terminologies: Minding the Representation Gap

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2503–2510 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2503 From Linguistic Resources to Ontology-Aware Terminologies: Minding the Representation Gap Giulia Speranza, Maria Pia di Buono, Johanna Monti and Federico Sangati UNIOR NLP Research Group University of Naples L’Orientale {gsperanza, mpdibuono, jmonti, fsangati}@unior.it Abstract Terminological resources have proven crucial in many applications ranging from Computer-Aided Translation tools to authoring softwares and multilingual and cross-lingual information retrieval systems. Nonetheless, with the exception of a few felicitous examples, such as the IATE (Interactive Terminology for Europe) Termbank, many terminological resources are not available in standard formats, such as Term Base eXchange (TBX), thus preventing their sharing and reuse. Yet, these terminologies could be improved associating the correspondent ontology-based information. The research described in the present contribution demonstrates the process and the methodologies adopted in the automatic conversion into TBX of such type of resources, together with their semantic enrichment based on the formalization of ontological information into terminologies. We present a proof-of-concept using the Italian Linguistic Resource for the Archaeological domain (developed according to Thesauri and Guidelines of the Italian Central Institute for the Catalogue and Documentation). Further, we introduce the conversion tool developed to support the process of creating ontology-aware terminologies for improving interoperability and sharing of existing language technologies and data sets. Keywords: Terminology, Linguistic Resources Conversion, Semantic Enrichment 1. Introduction The availability of terminological resources is crucial for experts in different fields; for instance, translators can inte- grate standard terminology in Term Base eXchange (TBX) format into their Computer-Aided Translation (CAT) tools, terminologists and linguists can reuse termbases in author- ing tool, Natural Language Processing (NLP) experts may use them for several applications, mainly multilingual and cross-lingual ones. One of the major problems for experts who do not possess specific knowledge of terms and phrase- ology of a domain is to detect and use specialised terms normally used by domain-experts. In addition, the choice of the corresponding translations for terms is not always straightforward because of polysemy and ambiguity prob- lems. Terminologies, developed by linguists, terminologists and domain experts, represent essential resources for language- based applications and platforms especially those con- nected with CAT and authoring tools. Terminology cre- ation and maintenance are tasks that determine the quality of the final product of a translation process. Good-quality and controlled terminology is critical for the success of a translation process, whether it is a human or an automatic one. Terminological databases have, indeed, an important role in translation technology, such as Machine Translation (MT), and in many multilingual applications as well, such as Mul- tilingual Information Retrieval (MLIR), Cross-language In- formation Retrieval (CLIR) applications among others. The IT sector should consider the importance of terminology in the translation process and integrate it into the tools. At the same time, terminological resources should be made available in standard formats so that they can be used ex- tensively in different applications, from CAT tools …

Content truncated to 500 words