Neural Architectures for Nested NER through Linearization

ACL 2019 Jana Strakov{\'a}Milan StrakaJan Hajic

We propose two neural network architectures for nested named entity recognition (NER), a setting in which named entities may overlap and also be labeled with more than one label. We encode the nested labels using a linearized scheme... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Compare
Named Entity Recognition ACE 2004 seq2seq+BERT+Flair F1 84.40 # 1
Named Entity Recognition ACE 2005 seq2seq+BERT+Flair F1 84.33 # 1
Named Entity Recognition CoNLL 2003 (English) LSTM-CRF+ELMo+BERT+Flair F1 93.38 # 3
Named Entity Recognition GENIA seq2seq+BERT+Flair F1 78.31 # 1