header.html

An official website of the European Union How do you know?      
European Commission logo

handle.jsp

cover
Tweets are specific text data when compared to general text. Although sentiment analysis over tweets has become very popular in the last decade for English, it is still difficult to find huge annotated corpora for non-English languages. The recent rise of the transformer models in Natural Language Processing allows to achieve unparalleled performances in many tasks, but these models need a consequent quantity of text to adapt to the tweet domain. We propose the use of a multilingual transformer model, that we pre-train over English tweets on which we apply data-augmentation using automatic translation to adapt the model to non-English languages. Our experiments in French, Spanish, German and Italian suggest that the proposed technique is an efficient way to improve the results of the transformers over small corpora of tweets in a non-English language.
2026-02-04
International Committee on Computational Linguistics
JRC121999
https://aclanthology.org/2020.coling-main.23/,    https://publications.jrc.ec.europa.eu/repository/handle/JRC121999,   
10.18653/v1/2020.coling-main.23 (online),   
NameCountryCityType
Datasets
IDTitlePublic URL
Dataset collections
IDAcronymTitlePublic URL
Scripts / source codes
DescriptionPublic URL
Additional supporting files
File nameDescriptionFile type 

footer.html