®®®® SIIA Público

Título del libro: 2021 9th International Conference In Software Engineering Research And Innovation (conisoft 2021)
Título del capítulo: Geolocation of Tweets in Spanish with Transformer Encoders

Autores UNAM:
ISMAEL EVERARDO BARCENAS PATIÃ?O; GUILLERMO GILBERTO MOLERO CASTILLO; EUGENIA JOSEFINA ALDECO PEREZ;
Autores externos:
Idioma:
Año de publicación:
2021
Palabras clave:

Geolocation; Transformer Encoders; Social Media; Tweets in Spanish

Resumen:

Tweet geolocation is very important in many contexts: disaster relief, opinion polling, recommendation systems, etc. There are some recent studies showing that tweets with geolocation tags are sparse in several settings. Current state of the art geolocation algorithms for tweets are based on natural language processing methods. Most of these algorithms have been tested in English. Transformers are machine learning models based on attention mechanisms. These models have been proven successful in many natural language processing and computer vision scenarios. In this paper, we propose a transformer model for tweet geolocation. We describe several experiments for tweets in Spanish located in the Mexican region.

Entidades citadas de la UNAM:
Fuente:



ISBN:
9781665443616
Editorial:
IEEE

Tipo de producto:
Proceedings Paper



DOI:
10.1109/CONISOFT52520.2021.00038