Universal dependency parsing

The task consists in parsing Spanish news articles following the Universal Dependency approach. Universal Dependencies (UD) is a framework for consistent annotation of grammar (parts of speech, morphological features and syntactic dependencies) across different human languages.

Publication
Jordi Porta-Zamorano, Luis Espinosa-Anke (2020) Overview of CAPITEL Shared Tasks at IberLEF 2020. Named Entity Recognition and Universal Dependencies Parsing. Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2020).
Competition
Named entity recognition and Universal Dependency parsing
Language
Spanish
NLP topic
parsing
Abstract task
Classification
Dataset
CAPITEL-UD
Year
2020
Publication link
http://ceur-ws.org/Vol-2664/c…
Ranking metric
Macro F1

Task results

System MacroPrecision MacroRecall MacroF1
ragerri 0.9043 0.9017 0.9030
ragerri 0.9039 0.9009 0.9023
ragerri 0.9036 0.9004 0.9019
mcuadros 0.8781 0.8809 0.8794
yanghao 0.8732 0.8843 0.8787

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.