CNN-Based Chinese NER with Lexicon Rethinking

  title={CNN-Based Chinese NER with Lexicon Rethinking},
  author={Tao Gui and Ruotian Ma and Qi Zhang and Lujun Zhao and Yu-Gang Jiang and X. Huang},
  • Tao Gui, Ruotian Ma, +3 authors X. Huang
  • Published in IJCAI 2019
  • Computer Science
  • Character-level Chinese named entity recognition (NER) that applies long short-term memory (LSTM) to incorporate lexicons has achieved great success. [...] Key Method The proposed method can model all the characters and potential words that match the sentence in parallel. In addition, the rethinking mechanism can address the word conflict by feeding back the high-level features to refine the networks. Experimental results on four datasets show that the proposed method can achieve better performance than both…Expand Abstract
    A Lexicon-Based Graph Neural Network for Chinese NER
    • 13
    • PDF
    TENER: Adapting Transformer Encoder for Named Entity Recognition
    • 11
    • Highly Influenced
    • PDF
    Porous Lattice-based Transformer Encoder for Chinese NER
    • 1
    FLAT: Chinese NER Using Flat-Lattice Transformer
    • 1
    • Highly Influenced
    • PDF
    Simplify the Usage of Lexicon in Chinese NER
    SLK-NER: Exploiting Second-order Lexicon Knowledge for Chinese NER
    End to End Chinese Lexical Fusion Recognition with Sememe Knowledge
    Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis


    Publications referenced by this paper.
    Adam: A Method for Stochastic Optimization
    • 49,691
    • PDF
    Distributed Representations of Words and Phrases and their Compositionality
    • 18,864
    • PDF
    End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
    • 1,303
    • PDF
    Chinese NER Using Lattice LSTM
    • 115
    • PDF
    A Shortest Path Dependency Kernel for Relation Extraction
    • 838
    • PDF