Funded by the Plan de Impulso de las Tecnologías del Lenguaje (PlanTL), Proposals can be submitted until April 30th, 2021.
The second edition of the task on semantic indexing of Spanish health-related texts called MESINESP2 invites researchers, medical and industrial professionals to develop automatic semantic indexing systems with structured medical vocabularies for Spanish documents. Sponsored by the Secretaría de Estado para el Avance Digital (SEAD) and the Plan de Impulso de las Tecnologías del Lenguaje (Plan TL), MESINESP2 aims to promote the development of semantic indexing tools of practical relevance of non-English content, determining the current state-of-the-art, identifying challenges, and comparing the strategies and results to those published for English data. Spanish researchers, medical, and industry professionals will be able to submit their validation predictions by 30 April 2021.
There is a pressing need to improve information access, retrieval, classification, semantic annotation as well as integration across multiple document types, in particular for health-related content such as literature, clinical trials and medicinal patents. Semantic indexing with medical vocabularies is an advantageous strategy to reduce costs and time bottlenecks in document indexing, and therefore improve access to this data. Most health and biomedicine related semantic indexing systems work only in English data, but a considerable amount of medically relevant content is also published in other languages, particularly clinical texts. As an example, the VHL Regional Portal, a search engine that brings together all scientific documents published in Spanish and Portuguese, has more than six million unique users searching for content in their native languages. The access to this non-English information is essential not only to professional medical users but also to researchers, public healthcare decision-makers, and other healthcare professionals to improve knowledge of new infectious diseases such as COVID19.
Luis Gascó, BSC researcher within the Text mining unit of BSC’s Life Science department, considers that “the systems resulting from MESINESP2 will provide a variety of use-case scenarios beyond literature indexing including competitive intelligence, prior art searches, complex search queries for systematic reviews, evidence-based medicine, decision making as well database curation, elaboration of clinical practice guidelines.”
The MESINESP2 task is part of the 9th BioASQ Workshop, which will be held as a Lab in CLEF 2021 on September 21-24, 2021 in Bucharest (Romania). BSC researchers organize this task in collaboration with the Biblioteca Nacional de Ciencias de la Salud and National Center for Scientific Research Demokritos.
Additional resources:
For more information, visit dedicated website here: https://temu.bsc.es/mesinesp2/ or please contact:
- Martin Krallinger by sending an email to mkrallin@bsc.es
- Luis Gascó by sending an email to lgasco@bsc.es
Caption: Figure: MESINESP2 shared-task overview