Umeå University's logo

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
Few-shot nested named entity recognition
Hefei University of Technology, 420 Jade Road, Hefei City, Anhui Province, Hefei, China.
Hefei University of Technology, 420 Jade Road, Hefei City, Anhui Province, Hefei, China.
Hefei University of Technology, 420 Jade Road, Hefei City, Anhui Province, Hefei, China.
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-7788-3986
Show others and affiliations
2024 (English)In: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 293, article id 111688Article in journal (Refereed) Published
Abstract [en]

While Named Entity Recognition (NER) is a widely studied task, making inferences of entities with only a few labeled data has been challenging, especially for entities with nested structures commonly existing in NER datasets. Unlike flat entities, entities and their nested entities are more likely to have similar semantic feature representations, drastically increasing difficulties in classifying different entity categories. This paper posits that the few-shot nested NER task warrants its own dedicated attention and proposes a Global-Biaffine Positive-Enhanced (GBPE) framework for this new task. Within the GBPE framework, we first develop the new Global-Biaffine span representation to capture the span global dependency information for each entity span to distinguish nested entities. We then formulate a unique positive-enhanced contrastive loss function to enhance the utility of specific positive samples in contrastive learning for larger margins. Lastly, by using these enlarged margins, we obtain better margin constraints and incorporate them into the nearest neighbor inference to predict the unlabeled entities. Extensive experiments on three nested NER datasets in English, German, and Russian show that GBPE outperforms baseline models on the 1-shot and 5-shot tasks in terms of F1 score.

Place, publisher, year, edition, pages
Elsevier, 2024. Vol. 293, article id 111688
Keywords [en]
Few-shot, Nested named entity recognition, Positive-enhanced contrastive loss
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:umu:diva-223235DOI: 10.1016/j.knosys.2024.111688Scopus ID: 2-s2.0-85189309268OAI: oai:DiVA.org:umu-223235DiVA, id: diva2:1852758
Funder
The Swedish Foundation for International Cooperation in Research and Higher Education (STINT), MG2020-8848Available from: 2024-04-19 Created: 2024-04-19 Last updated: 2024-04-19Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Jiang, Lili

Search in DiVA

By author/editor
Jiang, Lili
By organisation
Department of Computing Science
In the same journal
Knowledge-Based Systems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 15 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