Few-shot classification in named entity recognition task

Alexander Fritzler, Varvara Logacheva, Maksim Kretov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

34 Citations (Scopus)

Abstract

For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such as transfer learning or meta-learning. In this work we tackle Named Entity Recognition (NER) task using Prototypical Network - a metric learning technique. It learns intermediate representations of words which cluster well into named entity classes. This property of the model allows classifying words with extremely limited number of training examples, and can potentially be used as a zero-shot learning method. By coupling this technique with transfer learning we achieve well-performing classifiers trained on only 20 instances of a target class.

Original languageEnglish
Title of host publicationProceedings of the ACM Symposium on Applied Computing
PublisherAssociation for Computing Machinery
Pages993-1000
Number of pages8
ISBN (Print)9781450359337
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event34th Annual ACM Symposium on Applied Computing, SAC 2019 - Limassol, Cyprus
Duration: 8 Apr 201912 Apr 2019

Publication series

NameProceedings of the ACM Symposium on Applied Computing
VolumePart F147772

Conference

Conference34th Annual ACM Symposium on Applied Computing, SAC 2019
Country/TerritoryCyprus
CityLimassol
Period8/04/1912/04/19

Keywords

  • Few-shot learning
  • Named Entity Recognition
  • Prototypical networks
  • Semi-supervised learning
  • Transfer learning

Fingerprint

Dive into the research topics of 'Few-shot classification in named entity recognition task'. Together they form a unique fingerprint.

Cite this