Tasks
A task is an activity proposed with the purpose of solving a specific NLP problem, generally within the framework of a competition. Below is information about NLP tasks in Spanish from 2013 to the present.
Rest-Mex: Thematic Unsupervised Classification IberLEF 2023
- NLP topic: topic modeling
- Dataset: Rest-Mex 2023 Clustering
- Forum: IberLEF
- Competition: Rest-Mex 2023: Research on Sentiment Analysis Task for Mexican Tourist Texts
- Domain: News
- Language(s): Spanish
Relation extraction IberLEF 2021
- NLP topic: relation extraction
- Dataset: eHealth-KD-ES
- Forum: IberLEF
- Competition: eHealth Knowledge Discovery
- Domain: Health
- Language(s): Spanish, English
Detecting abbreviation-definition pairs IberEVAL 2018
- NLP topic: processing abbreviations
- Dataset: BARR2
- Forum: IberEVAL
- Competition: Biomedical Abbreviation Recognition and Resolution 2018
- Domain: Health
- Language(s): Spanish
Abbreviation resolution evaluation IberEVAL 2018
- NLP topic: processing abbreviations
- Dataset: BARR2
- Forum: IberEVAL
- Competition: Biomedical Abbreviation Recognition and Resolution 2018
- Domain: Health
- Language(s): Spanish
Abbreviation resolution IberEVAL 2018
- NLP topic: processing abbreviations
- Dataset: SPACCC
- Forum: IberEVAL
- Competition: Second Biomedical Abbreviation Recognition and Resolution (BARR2)
- Domain: Health
- Language(s): Spanish
Classification of political topics IberEVAL 2017
- NLP topic: topic modeling
- Dataset: COSET
- Forum: IberEVAL
- Competition: 1st Classification of Spanish Election Tweets Task
- Domain: Politics
- Language(s): Spanish
Abbreviation recognition and resolution IberEVAL 2017
- NLP topic: processing abbreviations
- Dataset: BARR
- Forum: IberEVAL
- Competition: Biomedical Abbreviation Recognition and Resolution
- Domain: Health
- Language(s): Spanish
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.