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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

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.

Original languageEnglish
Title of host publicationLREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
EditorsNicoletta 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
PublisherEuropean Language Resources Association (ELRA)
Pages1376-1381
Number of pages6
ISBN (Electronic)9791095546344
StatePublished - 2020
Event12th International Conference on Language Resources and Evaluation, LREC 2020 - Marseille, France
Duration: 11 May 202016 May 2020

Publication series

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

Conference

Conference12th International Conference on Language Resources and Evaluation, LREC 2020
Country/TerritoryFrance
CityMarseille
Period11/05/2016/05/20

Keywords

  • Document Classification
  • Machine Learning Methods
  • Named Entity Recognition
  • Opinion Mining
  • Other (Transfer Learning)
  • Sentiment Analysis
  • Statistical
  • Text categorisation

Fingerprint

Dive into the research topics of 'An evaluation of progressive neural networks for transfer learning in natural language processing'. Together they form a unique fingerprint.

Cite this