Abstract

This paper presents new methods for entity recognition and relation extraction tasks on partially labeled and unlabeled datasets. The proposed methods are based on techniques of semi-supervised, unsupervised and the transfer learning. We use the few-shot learning technique to construct specific algorithms for the new data sources without manual retraining. To compare the results with other studies, we conducted experiments on two benchmark datasets for the Russian language. The results for named entity recognition demonstrate significant improvement and outperform the state-of-the-art results. Our results for relation extraction are comparable to other research. We assume that a longer BERT fine-tuning will help to improve them, and we also plan to experiment with other few-shot learning methods in the near future.

Original languageEnglish
Title of host publicationProceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
Place of PublicationNovosibirsk, Russia
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages58-65
Number of pages8
ISBN (Electronic)9780738131115
ISBN (Print)978-0-7381-3112-2
DOIs
Publication statusPublished - 14 Nov 2020
Event2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020 - Virtual, Novosibirsk, Russian Federation
Duration: 14 Nov 202015 Nov 2020

Publication series

NameProceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

Conference

Conference2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
CountryRussian Federation
CityVirtual, Novosibirsk
Period14.11.202015.11.2020

Keywords

  • few-shot learning
  • Named entity recognition
  • relation extraction
  • transfer learning

OECD FOS+WOS

  • 6.02.OT LINGUISTICS
  • 1.02.EP COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Fingerprint Dive into the research topics of 'Using Few-Shot Learning Techniques for Named Entity Recognition and Relation Extraction'. Together they form a unique fingerprint.

Cite this