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
Cross-Encoded Meta Embedding towards Transfer Learning
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab. RISE ICE - Research Institutes of Sweden, Sweden.ORCID iD: 0000-0003-4293-6408
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Fluid and Experimental Mechanics.ORCID iD: 0000-0003-0398-1919
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0002-0546-116x
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
2020 (English)In: ESANN 2020 - Proceedings, ESANN , 2020, p. 631-636Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we generate word meta-embeddings from already existing embeddings using cross-encoding. Previous approaches can only work with words that exist in each source embedding, while the architecture presented here drops this requirement. We demonstrate the method using two pre-trained embeddings, namely GloVE and FastText. Furthermore, we propose additional improvements to the training process of the meta-embedding. Results on six standard tests for word similarity show that the meta-embedding trained outperforms the original embeddings. Moreover, this performance can be further increased with the proposed improvements, resulting in a competitive performance with those reported earlier.

Place, publisher, year, edition, pages
ESANN , 2020. p. 631-636
National Category
Computer Sciences Other Electrical Engineering, Electronic Engineering, Information Engineering Applied Mechanics
Research subject
Machine Learning; Electronic systems; Experimental Mechanics
Identifiers
URN: urn:nbn:se:ltu:diva-80637Scopus ID: 2-s2.0-85099006558OAI: oai:DiVA.org:ltu-80637DiVA, id: diva2:1462803
Conference
28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning,2-4 October, 2020, Bruges, Belgium (Online)
Note

ISBN för värdpublikation: 978-2-87587-074-2

Available from: 2020-08-31 Created: 2020-08-31 Last updated: 2022-10-31Bibliographically approved

Open Access in DiVA

No full text in DiVA

Scopus

Authority records

Brännvall, RickardÖhman, JohanKovács, GyörgyLiwicki, Marcus

Search in DiVA

By author/editor
Brännvall, RickardÖhman, JohanKovács, GyörgyLiwicki, Marcus
By organisation
Embedded Internet Systems LabFluid and Experimental Mechanics
Computer SciencesOther Electrical Engineering, Electronic Engineering, Information EngineeringApplied Mechanics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 325 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