Umeå University's logo

umu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • 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 universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0002-7788-3986
Vise andre og tillknytning
2024 (engelsk)Inngår i: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 293, artikkel-id 111688Artikkel i tidsskrift (Fagfellevurdert) 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.

sted, utgiver, år, opplag, sider
Elsevier, 2024. Vol. 293, artikkel-id 111688
Emneord [en]
Few-shot, Nested named entity recognition, Positive-enhanced contrastive loss
HSV kategori
Identifikatorer
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
Forskningsfinansiär
The Swedish Foundation for International Cooperation in Research and Higher Education (STINT), MG2020-8848Tilgjengelig fra: 2024-04-19 Laget: 2024-04-19 Sist oppdatert: 2024-04-19bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Jiang, Lili

Søk i DiVA

Av forfatter/redaktør
Jiang, Lili
Av organisasjonen
I samme tidsskrift
Knowledge-Based Systems

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 24 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf