no code implementations • COLING 2022 • Nelsi Melgarejo, Rodolfo Zevallos, Hector Gomez, John E. Ortega
In the effort to minimize the risk of extinction of a language, linguistic resources are fundamental.
no code implementations • MTSummit 2021 • John E. Ortega, Richard Alexander Castro Mamani, Jaime Rafael Montoya Samame
Low-resource languages sometimes take on similar morphological and syntactic characteristics due to their geographic nearness and shared history.
no code implementations • TDLE (LREC) 2022 • Iria de-Dios-Flores, Carmen Magariños, Adina Ioana Vladu, John E. Ortega, José Ramom Pichel, Marcos García, Pablo Gamallo, Elisa Fernández Rei, Alberto Bugarín-Diz, Manuel González González, Senén Barro, Xosé Luis Regueira
The development of language technologies (LTs) such as machine translation, text analytics, and dialogue systems is essential in the current digital society, culture and economy.
Cultural Vocal Bursts Intensity Prediction Machine Translation +1
no code implementations • 5 Oct 2023 • Chih-Chen Chen, William Chen, Rodolfo Zevallos, John E. Ortega
The application of self-supervision to speech representation learning has garnered significant interest in recent years, due to its scalability to large amounts of unlabeled data.
1 code implementation • 17 Apr 2023 • Shubham Vatsal, Adam Meyers, John E. Ortega
We compare our results for two classification tasks: (1) a broad classification task with 15 categories and (2) a fine-grained classification task with 279 categories.
1 code implementation • 15 Feb 2023 • Abteen Ebrahimi, Arya D. McCarthy, Arturo Oncevay, Luis Chiruzzo, John E. Ortega, Gustavo A. Giménez-Lugo, Rolando Coto-Solano, Katharina Kann
However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data.
no code implementations • 5 Dec 2022 • Ayush Singh, John E. Ortega
However, PLMs have been found to degrade in performance under distribution shift, a phenomenon that occurs when data at test-time does not come from the same distribution as the source training set.
no code implementations • 22 Jun 2022 • John E. Ortega
This work provides a survey of several networking cipher algorithms and proposes a method for integrating natural language processing (NLP) as a protective agent for them.