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
Continuous multilinguality with language vectors
Stockholm University, Faculty of Humanities, Department of Linguistics, Computational Linguistics.ORCID iD: 0000-0002-6027-4156
2017 (English)In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 2017, 644-649 p.Conference paper, Published paper (Refereed)
Abstract [en]

Most existing models for multilingual natural language processing (NLP) treat language as a discrete category, and make predictions for either one language or the other. In contrast, we propose using continuous vector representations of language. We show that these can be learned efficiently with a character-based neural language model, and used to improve inference about language varieties not seen during training. In experiments with 1303 Bible translations into 990 different languages, we empirically explore the capacity of multilingual language models, and also show that the language vectors capture genetic relationships between languages.

Place, publisher, year, edition, pages
2017. 644-649 p.
Series
ACL Anthology
Keyword [en]
language vectors, language embeddings, language modeling, parallel texts
National Category
Language Technology (Computational Linguistics)
Research subject
Computational Linguistics
Identifiers
URN: urn:nbn:se:su:diva-145546OAI: oai:DiVA.org:su-145546DiVA: diva2:1130219
Conference
15th Conference of the European Chapter of the Association for Computational Linguistics
Available from: 2017-08-08 Created: 2017-08-08 Last updated: 2017-08-15Bibliographically approved

Open Access in DiVA

fulltext(182 kB)15 downloads
File information
File name FULLTEXT01.pdfFile size 182 kBChecksum SHA-512
6271c32991c0e02197536435ccbb2b21a272a9e0e0eeaf9f31b9c84ba12071b931f95de22ec4f32bdcd4800b0963d872ecacb89033a4bbd0e61ea4be8ce5de46
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Östling, RobertTiedemann, Jörg
By organisation
Computational Linguistics
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 15 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 42 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