← Back to papers
2019 ACL ACL 2019

Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF

Abstract

AbstractIn 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.

🌉 Interdisciplinary Bridge — Deep Learning and Natural Language Processing
🧭 Keyword Pioneer — multilingual named entity recognition
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Anton Emelyanov , Ekaterina Artemova

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Understanding > Named Entity Recognition Natural Language Processing > Applications > Named Entity Recognition Deep Learning > Techniques > Attention

Keywords

sequence labeling attention mechanism named entity recognition bert language model recurrent neural network pretrained embedding multilingual named entity recognition bidirectional recurrent network
Download PDF

Related papers

What do phone embeddings learn about Phonology? 2019
Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages 2019
Understanding Undesirable Word Embedding Associations 2019
Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text 2019
Domain Adaptation of Neural Machine Translation by Lexicon Induction 2019