Chinese Named Entity Recognition Model Based on Multi-Task Learning
Compared to English, Chinese named entity recognition has lower performance due to the greater ambiguity in entity boundaries in Chinese text, making boundary prediction more difficult. While traditional models have attempted to enhance the definition of Chinese entity boundaries by incorporating ex...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/8/4770 |
| _version_ | 1827746116801658880 |
|---|---|
| author | Qin Fang Yane Li Hailin Feng Yaoping Ruan |
| author_facet | Qin Fang Yane Li Hailin Feng Yaoping Ruan |
| author_sort | Qin Fang |
| collection | DOAJ |
| description | Compared to English, Chinese named entity recognition has lower performance due to the greater ambiguity in entity boundaries in Chinese text, making boundary prediction more difficult. While traditional models have attempted to enhance the definition of Chinese entity boundaries by incorporating external features such as lexicons or glyphs, they have rarely disentangled the entity boundary prediction problem for separate study. In order to leverage entity boundary information, the named entity recognition task has been decomposed into two subtasks: boundary annotation and type annotation, and a multi-task learning network (MTL-BERT) has been proposed that combines a bidirectional encoder (BERT) model. This network performs joint encoding and specific decoding of the subtasks, enhancing the model’s feature extraction abilities by reinforcing the feature associations between subtasks. Multiple sets of experiments conducted on Weibo NER, MSRA, and OntoNote4.0 public datasets show that the F1 values of MTL-BERT reach 73.8%, 96.5%, and 86.7%, respectively, effectively improving the performance and efficiency of Chinese named entity recognition tasks. |
| first_indexed | 2024-03-11T05:16:57Z |
| format | Article |
| id | doaj.art-7838861899a448d098573eac2002cca5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:16:57Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7838861899a448d098573eac2002cca52023-11-17T18:08:59ZengMDPI AGApplied Sciences2076-34172023-04-01138477010.3390/app13084770Chinese Named Entity Recognition Model Based on Multi-Task LearningQin Fang0Yane Li1Hailin Feng2Yaoping Ruan3College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCompared to English, Chinese named entity recognition has lower performance due to the greater ambiguity in entity boundaries in Chinese text, making boundary prediction more difficult. While traditional models have attempted to enhance the definition of Chinese entity boundaries by incorporating external features such as lexicons or glyphs, they have rarely disentangled the entity boundary prediction problem for separate study. In order to leverage entity boundary information, the named entity recognition task has been decomposed into two subtasks: boundary annotation and type annotation, and a multi-task learning network (MTL-BERT) has been proposed that combines a bidirectional encoder (BERT) model. This network performs joint encoding and specific decoding of the subtasks, enhancing the model’s feature extraction abilities by reinforcing the feature associations between subtasks. Multiple sets of experiments conducted on Weibo NER, MSRA, and OntoNote4.0 public datasets show that the F1 values of MTL-BERT reach 73.8%, 96.5%, and 86.7%, respectively, effectively improving the performance and efficiency of Chinese named entity recognition tasks.https://www.mdpi.com/2076-3417/13/8/4770multi-task learningChinese named entity recognitionjoint learningfeature interactionbi-directional encoder (BERT) |
| spellingShingle | Qin Fang Yane Li Hailin Feng Yaoping Ruan Chinese Named Entity Recognition Model Based on Multi-Task Learning Applied Sciences multi-task learning Chinese named entity recognition joint learning feature interaction bi-directional encoder (BERT) |
| title | Chinese Named Entity Recognition Model Based on Multi-Task Learning |
| title_full | Chinese Named Entity Recognition Model Based on Multi-Task Learning |
| title_fullStr | Chinese Named Entity Recognition Model Based on Multi-Task Learning |
| title_full_unstemmed | Chinese Named Entity Recognition Model Based on Multi-Task Learning |
| title_short | Chinese Named Entity Recognition Model Based on Multi-Task Learning |
| title_sort | chinese named entity recognition model based on multi task learning |
| topic | multi-task learning Chinese named entity recognition joint learning feature interaction bi-directional encoder (BERT) |
| url | https://www.mdpi.com/2076-3417/13/8/4770 |
| work_keys_str_mv | AT qinfang chinesenamedentityrecognitionmodelbasedonmultitasklearning AT yaneli chinesenamedentityrecognitionmodelbasedonmultitasklearning AT hailinfeng chinesenamedentityrecognitionmodelbasedonmultitasklearning AT yaopingruan chinesenamedentityrecognitionmodelbasedonmultitasklearning |