Hierarchical Contextualized Representation for Named Entity Recognition

6 Nov 2019 Ying Luo Fengshun Xiao Hai Zhao

Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from larger scope, not only in the entire sentence, but also in the entire document (dataset)... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Named Entity Recognition CoNLL 2003 (English) Hierarchical + BERT F1 93.37 # 9
Named Entity Recognition CoNLL 2003 (English) Hierarchical F1 91.96 # 26
Named Entity Recognition Ontonotes v5 (English) Hierarchical + BERT F1 90.30 # 4
Named Entity Recognition Ontonotes v5 (English) Hierarchical F1 87.98 # 12

Methods used in the Paper


METHOD TYPE
Sigmoid Activation
Activation Functions
Tanh Activation
Activation Functions
Memory Network
Working Memory Models
BiLSTM
Bidirectional Recurrent Neural Networks
LSTM
Recurrent Neural Networks