Overview of CAPITEL Shared Tasks at IberLEF 2020: Named Entity Recognition and Universal Dependencies Parsing
This work addresses the problem of advancing NLP tools for Spanish text, but it is incremental as it focuses on organizing a shared task rather than introducing new methods.
The paper tackled the tasks of Named Entity Recognition and Universal Dependencies parsing for Spanish newswire articles, resulting in a shared task with seven teams submitting 13 runs and a newly annotated corpus called CAPITEL.
We present the results of the CAPITEL-EVAL shared task, held in the context of the IberLEF 2020 competition series. CAPITEL-EVAL consisted on two subtasks: (1) Named Entity Recognition and Classification and (2) Universal Dependency parsing. For both, the source data was a newly annotated corpus, CAPITEL, a collection of Spanish articles in the newswire domain. A total of seven teams participated in CAPITEL-EVAL, with a total of 13 runs submitted across all subtasks. Data, results and further information about this task can be found at sites.google.com/view/capitel2020.