Towards Robust Auxiliary Tasks for Language Adaptation

• Type: Article in International Conference Proceedings Book
• Date: 2021

Authors

Rocha, G (Author) Other; Henrique Lopes Cardoso (Author) FEUP

Conference proceedings International

Title: ESANN 2021 Proceedings - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Pages: 269-274

29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021

6 October 2021 through 8 October 2021

Indexing

Scopus - 269 Citations

Other information

Authenticus ID: P-00W-50H

DOI: 10.14428/esann/2021.es2021-134

Abstract (EN): To overcome the lack of annotated resources in less-resourced languages, unsupervised language adaptation methods have been explored. Based on multilingual word embeddings, Adversarial Training has been successfully employed in a variety of tasks and languages. With recent neural language models, empirical analysis on the task of natural language inference suggests that more challenging auxiliary tasks for Adversarial Training should be formulated to further improve language adaptation. We propose rethinking such auxiliary tasks for language adaptation. © 2021 ESANN Intelligence and Machine Learning. All rights reserved.

Language: English

Type (Professor's evaluation): Scientific