umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Improving Recurrent Neural Networks with Predictive Propagation for Sequence Labelling
The Australian E-Health Research Centre, CSIRO, Brisbane, QLD 4026, Australia.
(The Australian E-Health Research Centre, CSIRO, Brisbane, QLD 4026, Australia)
(The Australian E-Health Research Centre, CSIRO, Brisbane, QLD 4026, Australia)
Umeå University, Faculty of Science and Technology, Department of Computing Science. (Database and Data Mining Group)ORCID iD: 0000-0001-8820-2405
Show others and affiliations
2018 (English)In: Neural Information Processing: 25th International Conference, ICONIP 2018, Siem Reap, Cambodia, December 13-16, 2018, Proceedings, Part I, Springer, 2018, p. 452-462Conference paper, Published paper (Refereed)
Abstract [en]

Recurrent neural networks (RNNs) is a useful tool for sequence labelling tasks in natural language processing. Although in practice RNNs suffer a problem of vanishing/exploding gradient, their compactness still offers efficiency and make them less prone to overfitting. In this paper we show that by propagating the prediction of previous labels we can improve the performance of RNNs while keeping the number of parameters in RNNs unchanged and adding only one more step for inference. As a result, the models are still more compact and efficient than other models with complex memory gates. In the experiment, we evaluate the idea on optical character recognition and Chunking which achieve promising results.

Place, publisher, year, edition, pages
Springer, 2018. p. 452-462
Series
Lecture Notes in Computer Science ; vol 11301
Keywords [en]
Recurrent neural networks, NLP, Sequence labelling
National Category
Language Technology (Computational Linguistics)
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-154482DOI: 10.1007/978-3-030-04167-0_41ISBN: 978-3-030-04166-3 (print)ISBN: 978-3-030-04167-0 (electronic)OAI: oai:DiVA.org:umu-154482DiVA, id: diva2:1272344
Conference
The 25th International Conference on Neural Information Processing (ICONIP-2018), Siem Reap, Cambodia, December 13-16, 2018
Available from: 2018-12-19 Created: 2018-12-19 Last updated: 2019-08-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records BETA

Vu, Xuan-Son

Search in DiVA

By author/editor
Vu, Xuan-Son
By organisation
Department of Computing Science
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 125 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf