FGN: Fusion Glyph Network for Chinese Named Entity Recognition
This addresses the problem of improving accuracy in Chinese NER for NLP applications, representing an incremental advance by adding glyph-based features to existing methods.
The paper tackled Chinese Named Entity Recognition by incorporating latent glyph information from Chinese characters, proposing the Fusion Glyph Network (FGN) which achieved new state-of-the-art performance on four datasets.
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.