WikiMeSH: Multi Lingual MeSH Translations via Wikipedia

Abstract

Objective: The aim of this paper is to propose an extended translation of the MeSH thesaurus based on Wikipedia pages. Methods: A mapping was realized between each MeSH descriptor (preferred terms and synonyms) and corresponding Wikipedia pages. Results: A tool called “WikiMeSH” has been developed. Among the top 20 languages of this study, seven have currently no MeSH translations: Arabic, Catalan, Farsi (Iran), Mandarin Chinese, Korean, Serbian, and Ukrainian. For these seven languages, WikiMeSH is proposing a translation for 47% for Arabic to 34% for Serbian. Conclusion: WikiMeSH is an interesting tool to translate the MeSH thesaurus and other health terminologies and ontologies based on a mapping to Wikipedia pages.

Medical informatics and digital health multilingual ontology (MIMO): A tool to improve international collaborations

“…Among the top 20 languages of this study, seven currently have no MeSH translations: Arabic, Catalan, Farsi (Iran), Mandarin Chinese, Korean, Serbian, and Ukrainian. For these seven languages, WikiMeSH is proposing translations, for example, of 47 % to Arabic and 34 % to Serbian [43] ; MeSH synonyms: Synonyms and equivalent terms and concepts according to the MeSH but less used or less popular or more generally “related terms”; herein, we got “bibliometrics” MeSH synonyms in British English, American English, and Danish; DeCS synonyms: based on MeSH, DeCS (in Spanish: Descriptores en Ciencias de la Salud, in English: Health Sciences Descriptors) is a controlled and structured vocabulary in four languages (Spanish, Portuguese, French, and English). It expands the MeSH thesaurus, containing over 5,000 health concepts.…”

“…Among the top 20 languages of this study, seven currently have no MeSH translations: Arabic, Catalan, Farsi (Iran), Mandarin Chinese, Korean, Serbian, and Ukrainian. For these seven languages, WikiMeSH is proposing translations, for example, of 47 % to Arabic and 34 % to Serbian [43] ;…”

“…The next scheduled steps of the MIMO consist in: Developing a community of volunteer domain experts in the different fields of medical informatics and digital health having multilingual capabilities for expanding both the translations of the existing terms and developing a cross-translators (humans and AI-based systems) validation process; Expanding MIMO to other non-European languages, such as Arabic, Chinese, and Russian, as part of the UN official languages in addition to English, French, and Spanish [50] ; Developing tools allowing to capture existing translations in open data resources and so expanding MIMO to other languages supported by multilingual collaborative communities [43] ; Adding vocabularies of trending or emerging fields in medical informatics and digital health, such as “One Digital Health” [51] , “Accident and Emergency Informatics” [52] , robotics in healthcare systems and industry [53] ; Moving MIMO to a complete multilingual ontology to facilitate its maintenance and expansion to support efficient international health technologies-related projects [54] . …”

“…Developing tools allowing to capture existing translations in open data resources and so expanding MIMO to other languages supported by multilingual collaborative communities [43] ;…”

Digital Health Multilingual Ontology to Index Teaching Resources

“…A copy of these translations was integrated into MIMO. An added list of translations was added from the WikiMeSH algorithm [15] that we have recently developed to enhance the MIMO translations in European languages and above. A specific module was devoted to the manual curation of these translations because this mapping could generate false positives in case of polysemy (multiple related meanings) or ambiguous acronyms.…”