MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition
Named Entity Recognition (NER) aims to automatically extract specific entities from unstructured text. Compared with English NER, Chinese NER faces challenges due to heterophony, where the same Chinese character may have different pronunciations and meanings. Additionally, the lack of clear separato...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10980313/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849313227363581952 |
|---|---|
| author | Pu Li Guopeng Cheng Guojun Deng Shuanghong Qu Min Huang Guoxiang Li |
| author_facet | Pu Li Guopeng Cheng Guojun Deng Shuanghong Qu Min Huang Guoxiang Li |
| author_sort | Pu Li |
| collection | DOAJ |
| description | Named Entity Recognition (NER) aims to automatically extract specific entities from unstructured text. Compared with English NER, Chinese NER faces challenges due to heterophony, where the same Chinese character may have different pronunciations and meanings. Additionally, the lack of clear separators between Chinese characters exacerbates these challenges, leading to difficulties in boundary detection and entity category determination. Inspired by the hieroglyphic and phonetic features of Chinese characters, this study proposes a multi-feature fusion embedding model (MP-NER). The model employs CNN for extracting radicals and phonetic features of Chinese characters, combines the encoded information from these features with pre-trained word vectors to generate fusion embedding vectors, and uses a fully-connected layer for feature transformation. Experiments were conducted on the Chinese benchmark datasets Resume, Weibo and MSRA. Compared to current mainstream models, the proposed model demonstrates superior performance in terms of F1 score, F1 score stability, and individual entity recognition accuracy. Ablation experiments further validate the effectiveness of the introduced radicals and phonetic features. The experimental results demonstrate that this model effectively captures the semantic information of Chinese characters, addresses the problem of Chinese character heterophony, and improves entity recognition performance. The code and datasets available at: <uri>https://github.com/FAKLITS/MP-NER</uri> |
| format | Article |
| id | doaj-art-71a2e8caa53542ee82e332fbc887d4ce |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-71a2e8caa53542ee82e332fbc887d4ce2025-08-20T03:52:51ZengIEEEIEEE Access2169-35362025-01-0113784277844010.1109/ACCESS.2025.356590810980313MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity RecognitionPu Li0https://orcid.org/0000-0002-5703-9905Guopeng Cheng1https://orcid.org/0009-0006-7927-3838Guojun Deng2https://orcid.org/0009-0004-4917-1668Shuanghong Qu3https://orcid.org/0009-0006-3172-9656Min Huang4https://orcid.org/0009-0001-6385-2636Guoxiang Li5College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaCollege of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaHenan Zhongcheng Information Technology Company Ltd., Zhengzhou, ChinaCollege of Mathematics and Information Science, Zhengzhou University of Light Industry, Zhengzhou, ChinaCollege of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaDepartment of Academic Affairs, Guangxi University of Finance and Economics, Nanning, ChinaNamed Entity Recognition (NER) aims to automatically extract specific entities from unstructured text. Compared with English NER, Chinese NER faces challenges due to heterophony, where the same Chinese character may have different pronunciations and meanings. Additionally, the lack of clear separators between Chinese characters exacerbates these challenges, leading to difficulties in boundary detection and entity category determination. Inspired by the hieroglyphic and phonetic features of Chinese characters, this study proposes a multi-feature fusion embedding model (MP-NER). The model employs CNN for extracting radicals and phonetic features of Chinese characters, combines the encoded information from these features with pre-trained word vectors to generate fusion embedding vectors, and uses a fully-connected layer for feature transformation. Experiments were conducted on the Chinese benchmark datasets Resume, Weibo and MSRA. Compared to current mainstream models, the proposed model demonstrates superior performance in terms of F1 score, F1 score stability, and individual entity recognition accuracy. Ablation experiments further validate the effectiveness of the introduced radicals and phonetic features. The experimental results demonstrate that this model effectively captures the semantic information of Chinese characters, addresses the problem of Chinese character heterophony, and improves entity recognition performance. The code and datasets available at: <uri>https://github.com/FAKLITS/MP-NER</uri>https://ieeexplore.ieee.org/document/10980313/Chinese named entity recognitionfeatures fusionphonetic featureradicals feature |
| spellingShingle | Pu Li Guopeng Cheng Guojun Deng Shuanghong Qu Min Huang Guoxiang Li MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition IEEE Access Chinese named entity recognition features fusion phonetic feature radicals feature |
| title | MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition |
| title_full | MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition |
| title_fullStr | MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition |
| title_full_unstemmed | MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition |
| title_short | MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition |
| title_sort | mp ner morpho phonological integration embedding for chinese named entity recognition |
| topic | Chinese named entity recognition features fusion phonetic feature radicals feature |
| url | https://ieeexplore.ieee.org/document/10980313/ |
| work_keys_str_mv | AT puli mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition AT guopengcheng mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition AT guojundeng mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition AT shuanghongqu mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition AT minhuang mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition AT guoxiangli mpnermorphophonologicalintegrationembeddingforchinesenamedentityrecognition |