CLJun 21, 2019

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

arXiv:1906.09978v11091 citations
Originality Synthesis-oriented
AI Analysis

This work addresses multilingual NER for Slavic languages, but it is incremental as it applies existing methods to new data without fine-tuning.

The paper tackles multilingual named entity recognition by using multilingual BERT embeddings with bidirectional recurrent networks, attention, and NCRF, achieving competitive results on Bulgarian, Czech, Polish, and Russian texts from the BSNLP shared task dataset.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes