Chinese Named Entity Recognition with Changed BiLSTM and CRF

EasyChair Preprint 1028

Abstract

This paper is aimed at improving name entity recognition(NER) accuracy. We replace the traditional bidirectional long short-term memory network (BiLSTM) with a changed BiLSTM, and then uses a CRF layer behind the changed BiLSTM layer to add the probabilistic relation of different Chinese characters.

Keyphrases: CRF, Changed BiLSTM, NER

@booklet{EasyChair:1028,
  author    = {Jie Ren and Jing Liang and Chenkai Zhao},
  title     = {Chinese Named Entity Recognition with Changed BiLSTM and CRF},
  howpublished = {EasyChair Preprint 1028},
  year      = {EasyChair, 2019}}