Using Chinese Glyphs for Named Entity Recognition

TL;DR

This paper introduces CNN-based models that leverage the semantic information of Chinese radicals for NER, eliminating the need for external features like gazetteers, and achieves state-of-the-art results on multiple datasets.

Contribution

The paper proposes a novel CNN-based approach using Chinese character radicals for NER, improving performance without relying on external knowledge sources.

Findings

Achieved a +0.64 F1 score improvement on Chinese OntoNotes v5.0

Set a new state-of-the-art F1 score of 71.81 on Weibo dataset

Showed competitive results on ResumeNER dataset

Abstract

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.