Unified Named Entity Recognition as Word-Word Relation Classification

So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied individually. Recently, a growing interest has been built for unified NER, tackling the above three jobs concurrently with one single model. Current best-performing methods mainly include span-based and sequence-to-sequence models, where unfortunately the former merely focus on boundary identification and the latter may suffer from exposure bias. In this work, we present a novel alternative by modeling the unified NER as word-word relation classification, namely W^2NER. The architecture resolves the kernel bottleneck of unified NER by…

• NN
  National Natural Science Foundation of China

  Awards: 62176187, 61772378, No. 62176187
• MO
  Ministry of Education of the People's Republic of China

  Awards: 22YJCZH064, 18JZD015
• WU
  Wuhan University
• NK
  National Key Research and Development Program of China

  Award: 2017YFC1200500
• FR
  Fundamental Research Funds for the Central Universities