The international competition ProfNER-ST consists in the identification of occupations (ProfNER) in tweets written mostly in Castilian Spanish, after selecting health-relevant content. Funded by the Plan de Impulso de las Tecnologías del Lenguaje (Plan TL), BSC experts are involved in the Social Media Mining for Health Applications (#SMM4H) shared task that invites researchers to develop systems to solve health informatics challenges for social media. In particular, this task is focused on Twitter data related to Covid-19 and lock-downs. Spanish researchers will be able to submit their validation predictions by 25 February 2021.
Martin Krallinger, coordinator of the Natural Language Processing group in the BSC and main promoter of the competition, considers that “detecting vulnerable occupations is key to prepare preventive measures, be it due to their risk of direct exposure to the Covid-19 virus or due to mental health issues associated with work-related aspects”.
The #SMM4H task is part of the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics and is organized by experts of the Barcelona Supercomputing Center (Spain), University of Pennsylvania (USA), Emory University (USA), Kazan Federal University (Russia), Université d’Orléans (France).
Additional resources:
- Web
- Gold Standard corpus
- Annotation guidelines (in Spanish)
- Annotation guidelines (in English)
- Occupations gazetteer
Video: https://youtu.be/V2d51nlPtzQ
For more information, please contact:
Martin Krallinger: encargo-pln-life@bsc.es
Antonio Miranda: antonio.miranda@bsc.es