no code implementations • NAACL (WOAH) 2022 • Ayme Arango Monnar, Jorge Perez, Barbara Poblete, Magdalena Saldaña, Valentina Proust
We propose a comparative framework for quickly conducting comparative experiments using different previously published models. In addition, we set up a Codalab competition for further comparison of new models in a standard scenario, that is, data partitions and evaluation metrics.
1 code implementation • 5 Sep 2022 • Cinthia Sánchez, Hernan Sarmiento, Andres Abeliuk, Jorge Pérez, Barbara Poblete
In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data.
no code implementations • 30 Apr 2021 • Aymé Arango, Jorge Pérez, Barbara Poblete
Our proposal constitutes, to the best of our knowledge, the first attempt for constructing multilingual specific-task representations.
no code implementations • IJCNLP 2019 • Henry Rosales-M{\'e}ndez, Aidan Hogan, Barbara Poblete
The Entity Linking (EL) task identifies entity mentions in a text corpus and associates them with an unambiguous identifier in a Knowledge Base.