Talk · Science and Artificial Intelligence Conference · November 14, 2020
Using Few-Shot Learning Techniques for Named Entity Recognition and Relation Extraction
Ivan Bondarenko, Sergey Berezin, Alexey Pauls, Tatiana Viktorovna Batura, Yuliya Rubtsova, Тучинов Баир Николаевич
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.
More by Tatiana Batura
- Entity Linking of Scientific Terms in Specialized Domains and Low-Resource SettingsApplied Sciences · 2026
- SciMDIX: A dataset for aspect extraction from multi-domain scientific documents in Kazakh and RussianProcedia Computer Science · 2026 · Citations: 1
- From text to knowledge: Entity linking of scientific terms to WikipediaBulletin of the Novosibirsk Computing Center Series Computer Science · 2025
- Kazakh Text Classification using Deep Learning ApproachesInternational Conference on Computer Science and Engineering · 2025 · Citations: 1
