Article · Bulletin of the Novosibirsk Computing Center Series Computer Science · February 9, 2024
Comparison of ELMO-based models on the named entity recognition task
Artem Skiba, Tatiana Viktorovna Batura
Abstract
This paper presents a comparison of ELMO-based models.The comparison was performed on data in the Russian language for the task of named entity recognition (NER).The paper also discusses a comparison of the architectures based on the Simple Recurrent Unit (SRU) and Gated Recurrent Unit (GRU).All the models compared were trained on a corpus of news texts in the Russian language taken from the Wikinews resource and were assessed on the Russian subsets of the WikiNEuRal and MultiCoNER datasets.The datasets and original code are available at https://github.com/Abiks/distributed-semantic-models.The results obtained suggest that the SRU architecture is promising for solving the NER task and it provides a high training speed.Also, the quality of NER models based on uncontextualized char-based embeddings was found to be comparable with other models discussed herein.This highlights the advantage of using characterbased embeddings as part of the RNN or a transformer-based model because of their robustness to typos.However, the architectural details of the char-based block need further research.
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
