Detection of lexical borrowings

The task consists in detecting lexical borrowings (coming mostly from English) in Spanish newswire texts. Lexical borrowings are words from other languages  that have recently been imported into Spanish.

Systems must delimitate lexical borrowings using BIO encoding and annotate them with 2 tags: ENG: for English borrowings  and OTHER: for borrowings from other languages.

Publication
Elena Alvarez Mellado, Luis Espinosa Anke, Julio Gonzalo Arroyo, Constantine Lignos, Jordi Porta Zamorano (2021) Overview of ADoBo 2021: Automatic Detection of Unassimilated Borrowings in the Spanish Press. Procesamiento del Lenguaje Natural, 67, septiembre de 2021, pp. 277-285.
Competition
ADOBO: Detection of lexical borrowings
Language
Spanish
URL Task
https://adobo-task.github.io/
NLP topic
text classification
Abstract task
Sequence labeling
Dataset
ADoBo
Year
2021
Publication link
http://journal.sepln.org/sepl…
Ranking metric
F1

Task results

System Precision Recall F1
Versae 0.6007 0.8148 0.6915
BERT4EVER 0.7296 0.2646 0.3883

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.