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.
HUHU - Hurtful humour detection IberLEF 2023
- NLP topic: processing humor
- Dataset: HUHU 2023
- Forum: IberLEF
- Competition: HUHU: HUrtful HUmour - Detection of humour spreading prejudice on Twitter
- Domain: Social
- Language(s): Spanish
- NLP topic: text classification
- Dataset: ClinAIS 2023
- Forum: IberLEF
- Competition: ClinAIS: Automatic identification of sections in clinical documents
- Domain: Health
- Language(s): Spanish
HUHU - Prejudice Target Detection IberLEF 2023
- NLP topic: processing humor
- Dataset: HUHU 2023
- Forum: IberLEF
- Competition: HUHU: HUrtful HUmour - Detection of humour spreading prejudice on Twitter
- Domain: Social
- Language(s): Spanish
JOKER: Pun detection in Spanish CLEF 2023
- NLP topic: processing humor
- Dataset: JOKER 2023 ES
- Forum: CLEF
- Competition: JOKER: Automatic Wordplay Analysis
- Domain: Social
- Language(s): Spanish
JOKER: Pun location in Spanish CLEF 2023
- NLP topic: processing humor
- Dataset: JOKER 2023 ES
- Forum: CLEF
- Competition: JOKER: Automatic Wordplay Analysis
- Domain: Social
- Language(s): Spanish
- NLP topic: text classification
- Dataset: SMM4H-tweets-es-2022
- Forum: COLING
- Competition: Seventh Social Media Mining for Health Applications
- Domain: Health
- Language(s): Spanish
Occupation and occupation holder detection IberLEF 2021
- NLP topic: text classification
- Dataset: MEDDOPROF
- Forum: IberLEF
- Competition: Recognition, classification and normalization of professions and occupations from medical texts
- Domain: Health
- Language(s): Spanish
Humor logic mechanism classification IberLEF 2021
- NLP topic: processing humor
- Dataset: HAHA
- Forum: IberLEF
- Competition: Detecting, Rating and Analyzing Humor in Spanish
- Domain:
- Language(s): Spanish
Named entity normalization IberLEF 2021
- NLP topic: text classification
- Dataset: MEDDOPROF
- Forum: IberLEF
- Competition: Recognition, classification and normalization of professions and occupations from medical texts
- Domain: Health
- Language(s): Spanish
Humor detection IberLEF 2021
- NLP topic: processing humor
- Dataset: HAHA
- Forum: IberLEF
- Competition: Detecting, Rating and Analyzing Humor in Spanish
- Domain:
- Language(s): Spanish
Irony detection IberLEF 2019
- NLP topic: processing humor
- Dataset: IDAT-SP-EU, IDAT-SP-MEX, IDAT-SP-CUBA
- Forum: IberLEF
- Competition: Irony Detection in Spanish Variants
- Domain:
- Language(s): Spanish (Cuba), Spanish (Mexico), Spanish (Spain)
Irony detection IberLEF 2019
- NLP topic: processing humor
- Dataset: IDAT-SP-EU, IDAT-SP-MEX, IDAT-SP-CUBA
- Forum: IberLEF
- Competition: Irony Detection in Spanish Variants
- Domain:
- Language(s): Spanish (Cuba), Spanish (Mexico), Spanish (Spain)
Humor detection IberLEF 2019
- NLP topic: processing humor
- Dataset: HAHA
- Forum: IberLEF
- Competition: HAHA 2019: Humor Analysis based on Human Annotation
- Domain:
- Language(s): Spanish
Irony detection IberLEF 2019
- NLP topic: processing humor
- Dataset: IDAT-SP-EU, IDAT-SP-MEX, IDAT-SP-CUBA
- Forum: IberLEF
- Competition: Irony Detection in Spanish Variants
- Domain:
- Language(s): Spanish (Cuba), Spanish (Mexico), Spanish (Spain)
Humor detection IberEVAL 2018
- NLP topic: processing humor
- Dataset: HAHA
- Forum: IberEVAL
- Competition: Humor Analysis based on Human Annotation (HAHA)
- Domain:
- Language(s): Spanish
Emoji prediction SEMEVAL 2018
- NLP topic: text classification
- Dataset: Tweets emojis-ES
- Forum: SEMEVAL
- Competition: SemEval 2018 Task 2: Multilingual Emoji Prediction
- Domain:
- Language(s): Spanish, English
Author categorisation CLEF 2014
- NLP topic: text classification
- Dataset: RepLab-2014-Profiling
- Forum: CLEF
- Competition: RepLab 2014: Author Profiling and Reputation Dimensions for Online Reputation Management
- Domain: Finance
- 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.
