Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF
Computation and Language
2023-10-04 v1
Abstract
In this paper we tackle multilingual named entity recognition task. We use the BERT Language Model as embeddings with bidirectional recurrent network, attention, and NCRF on the top. We apply multilingual BERT only as embedder without any fine-tuning. We test out model on the dataset of the BSNLP shared task, which consists of texts in Bulgarian, Czech, Polish and Russian languages.
Cite
@article{arxiv.1906.09978,
title = {Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF},
author = {Anton A. Emelyanov and Ekaterina Artemova},
journal= {arXiv preprint arXiv:1906.09978},
year = {2023}
}
Comments
BSNLP Shared Task 2019 paper. arXiv admin note: text overlap with arXiv:1806.05626 by other authors