Detail publikace

Transferability and Stability of Learning With Limited Labelled Data in Multilingual Text Domain

PECHER, B. SRBA, I. BIELIKOVÁ, M.

Originální název

Transferability and Stability of Learning With Limited Labelled Data in Multilingual Text Domain

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Using the learning with limited labelled data approaches to improve performance in multilingual domains, where small amount of labels are spread spread across languages and tasks, requires knowing the transferability of these approaches to new datasets and tasks. However, the lower data availability makes the learning with limited labelled data unstable, resulting in randomness invalidating the investigation, when it is not taken into consideration. Nevertheless, previous studies that perform benchmarking and investigation of such approaches mostly ignore the effects of randomness. In our work, we want to remedy this by investigating the stability and transferability, for effective use in the multilingual domains with specific characteristics.

Klíčová slova

Artificial intelligence, Classification (of information), Text processing

Autoři

PECHER, B.; SRBA, I.; BIELIKOVÁ, M.

Vydáno

28. 7. 2022

Nakladatel

International Joint Conferences on Artificial Intelligence

Místo

Vienna

ISBN

978-1-956792-00-3

Kniha

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Doctoral Consortium

Strany od

5869

Strany do

5870

Strany počet

2

URL

https://www.ijcai.org/proceedings/2022/837

BibTex

@inproceedings{BUT180394,
  author="PECHER, B. and SRBA, I. and BIELIKOVÁ, M.",
  title="Transferability and Stability of Learning With Limited Labelled Data in Multilingual Text Domain",
  booktitle="Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Doctoral Consortium",
  year="2022",
  pages="5869--5870",
  publisher="International Joint Conferences on Artificial Intelligence",
  address="Vienna",
  doi="10.24963/ijcai.2022/837",
  isbn="978-1-956792-00-3",
  url="https://www.ijcai.org/proceedings/2022/837"
}