FGN: Fusion Glyph Network for Chinese Named Entity Recognition

15 Jan 2020  ·  Zhenyu Xuan, Rui Bao, Shengyi Jiang ·

Chinese NER is a challenging task. As pictographs, Chinese characters contain latent glyph information, which is often overlooked. In this paper, we propose the FGN, Fusion Glyph Network for Chinese NER. Except for adding glyph information, this method may also add extra interactive information with the fusion mechanism. The major innovations of FGN include: (1) a novel CNN structure called CGS-CNN is proposed to capture both glyph information and interactive information between glyphs from neighboring characters. (2) we provide a method with sliding window and Slice-Attention to fuse the BERT representation and glyph representation for a character, which may capture potential interactive knowledge between context and glyph. Experiments are conducted on four NER datasets, showing that FGN with LSTM-CRF as tagger achieves new state-of-the-arts performance for Chinese NER. Further, more experiments are conducted to investigate the influences of various components and settings in FGN.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Chinese Named Entity Recognition MSRA FGN F1 95.64 # 7
Chinese Named Entity Recognition OntoNotes 4 FGN F1 82.04 # 5
Chinese Named Entity Recognition Resume NER FGN F1 96.79 # 2
Chinese Named Entity Recognition Weibo NER FGN F1 71.25 # 3