liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Interpretable Word Embeddings via Informative Priors
Linköping University, The Institute for Analytical Sociology, IAS.
Linköping University, The Institute for Analytical Sociology, IAS.
Aalto University.
2019 (English)In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) / [ed] Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan, 2019, Vol. D19-1, p. 6324-6330, article id D19-1661Conference paper, Published paper (Refereed)
Abstract [en]

Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dimensions for probabilistic word embeddings. Experimental results show that sensible priors can capture latent semantic concepts better than or on-par with the current state of the art, while retaining the simplicity and generalizability of using priors.

Place, publisher, year, edition, pages
2019. Vol. D19-1, p. 6324-6330, article id D19-1661
National Category
Language Technology (Computational Linguistics) Social Sciences Interdisciplinary Sociology (excluding Social Work, Social Psychology and Social Anthropology)
Identifiers
URN: urn:nbn:se:liu:diva-161824OAI: oai:DiVA.org:liu-161824DiVA, id: diva2:1369269
Conference
Empirical Methods in Natural Language Processing
Funder
Swedish Research Council, 2018–05170Available from: 2019-11-11 Created: 2019-11-11 Last updated: 2019-11-11

Open Access in DiVA

No full text in DiVA

Search in DiVA

By author/editor
Hurtado Bodell, Miriam
By organisation
The Institute for Analytical Sociology, IAS
Language Technology (Computational Linguistics)Social Sciences InterdisciplinarySociology (excluding Social Work, Social Psychology and Social Anthropology)

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 11 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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