An evaluation of progressive neural networks for transfer learning in natural language processing

Gerhard Hagerer, Abdul Moeed, Sumit Dugar, Sarthak Gupta, Mainak Ghosh, Hannah Danner, Oliver Mitevski, Andreas Nawroth, Georg Groh

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

4 Zitate (Scopus)

Abstract

A major challenge in modern neural networks is the utilization of previous knowledge for new tasks in an effective manner, otherwise known as transfer learning. Fine-tuning, the most widely used method for achieving this, suffers from catastrophic forgetting. The problem is often exacerbated in natural language processing (NLP). In this work, we assess progressive neural networks (PNNs) as an alternative to fine-tuning. The evaluation is based on common NLP tasks such as sequence labeling and text classification. By gauging PNNs across a range of architectures, datasets, and tasks, we observe improvements over the baselines throughout all experiments.

OriginalspracheEnglisch
TitelLREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
Redakteure/-innenNicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Herausgeber (Verlag)European Language Resources Association (ELRA)
Seiten1376-1381
Seitenumfang6
ISBN (elektronisch)9791095546344
PublikationsstatusVeröffentlicht - 2020
Veranstaltung12th International Conference on Language Resources and Evaluation, LREC 2020 - Marseille, Frankreich
Dauer: 11 Mai 202016 Mai 2020

Publikationsreihe

NameLREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings

Konferenz

Konferenz12th International Conference on Language Resources and Evaluation, LREC 2020
Land/GebietFrankreich
OrtMarseille
Zeitraum11/05/2016/05/20

Fingerprint

Untersuchen Sie die Forschungsthemen von „An evaluation of progressive neural networks for transfer learning in natural language processing“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren