Using Chinese Glyphs for Named Entity Recognition
This work addresses the problem of reducing external knowledge dependencies in Chinese NER for NLP practitioners, though it is incremental as it builds on existing CNN and BERT-based models.
The paper tackles Chinese Named Entity Recognition by using lexicographic features from Chinese character radicals instead of traditional features like POS tags, achieving improvements such as a +0.64 F1 score on Chinese OntoNotes v5.0 and a state-of-the-art 71.81 F1 on the Weibo dataset.
Most Named Entity Recognition (NER) systems use additional features like part-of-speech (POS) tags, shallow parsing, gazetteers, etc. Such kind of information requires external knowledge like unlabeled texts and trained taggers. Adding these features to NER systems have been shown to have a positive impact. However, sometimes creating gazetteers or taggers can take a lot of time and may require extensive data cleaning. In this paper for Chinese NER systems, we do not use these traditional features but we use lexicographic features of Chinese characters. Chinese characters are composed of graphical components called radicals and these components often have some semantic indicators. We propose CNN based models that incorporate this semantic information and use them for NER. Our models show an improvement over the baseline BERT-BiLSTM-CRF model. We set a new baseline score for Chinese OntoNotes v5.0 and show an improvement of +.64 F1 score. We present a state-of-the-art F1 score on Weibo dataset of 71.81 and show a competitive improvement of +0.72 over baseline on ResumeNER dataset.