MFE-NER: Multi-feature Fusion Embedding for Chinese Named Entity Recognition
This addresses a specific linguistic challenge in Chinese NER for NLP applications, but it is incremental as it builds on existing pre-trained models with feature enhancements.
The paper tackles the problem of character substitution in Chinese Named Entity Recognition by proposing MFE-NER, a lightweight method that fuses glyph and phonetic features to help pre-trained language models handle this issue with limited extra cost, resulting in especially good performance in detecting character substitutions and slight overall improvement.
In Chinese Named Entity Recognition, character substitution is a complicated linguistic phenomenon. Some Chinese characters are quite similar as they share the same components or have similar pronunciations. People replace characters in a named entity with similar characters to generate a new collocation but referring to the same object. As a result, it always leads to unrecognizable or mislabeling errors in the NER task. In this paper, we propose a lightweight method, MFE-NER, which fuses glyph and phonetic features, to help pre-trained language models handle the character substitution problem in the NER task with limited extra cost. Basically, in the glyph domain, we disassemble Chinese characters into Five-Stroke components to represent structure features. In the phonetic domain, an improved phonetic system is proposed in our work, making it reasonable to describe phonetic similarity among Chinese characters. Experiments demonstrate that our method performs especially well in detecting character substitutions while slightly improving the overall performance of Chinese NER.