Аннотация

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.

Язык оригиналаанглийский
Название основной публикацииProceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
Место публикацииNovosibirsk, Russia
ИздательInstitute of Electrical and Electronics Engineers Inc.
Страницы58-65
Число страниц8
ISBN (электронное издание)9780738131115
ISBN (печатное издание)978-0-7381-3112-2
DOI
СостояниеОпубликовано - 14 ноя 2020
Событие2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020 - Virtual, Novosibirsk, Российская Федерация
Продолжительность: 14 ноя 202015 ноя 2020

Серия публикаций

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

Конференция

Конференция2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
СтранаРоссийская Федерация
ГородVirtual, Novosibirsk
Период14.11.202015.11.2020

Предметные области OECD FOS+WOS

  • 6.02.OT ЛИНГВИСТИКА
  • 1.02.EP ИНФОРМАТИКА, ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ

Fingerprint Подробные сведения о темах исследования «Using Few-Shot Learning Techniques for Named Entity Recognition and Relation Extraction». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать