Few-shot Named Entity Ｒecognition for Medical Text
Aiming at the problem that medical text named entity recognition lacks sufficient labeled data，a newly named entity recognition deep neural network and data enhancement method is proposed. First of all，the Bert word vector is extended with pinyin and strokes of Chinese characters to make it contain...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin University of Science and Technology Publications
2021-08-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1998 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849771931664908288 |
|---|---|
| author | QIN Jian HOU Jian-xin XIE Yi-ning HE Yong-jun |
| author_facet | QIN Jian HOU Jian-xin XIE Yi-ning HE Yong-jun |
| author_sort | QIN Jian |
| collection | DOAJ |
| description | Aiming at the problem that medical text named entity recognition lacks sufficient labeled data，a newly named entity recognition deep neural network and data enhancement method is proposed. First of all，the Bert word vector is extended with pinyin and strokes of Chinese characters to make it contain more useful information. Then the named entity recognition model and the word segmentation model are jointly trained to enhance the model's ability to recognize entity boundaries. Finally，an improved data enhancement method is used to process the training data，which can increase the recognition effect of the model on named entities while avoiding overfitting of the model. The experimental results on the electronic medical record text provided by CCKS-2019 show that the proposed method can effectively improve the accuracy of named entity recognition in the case of small samples and the recognition rate can still be maintained without a significant decrease when the training data is reduced by half. |
| format | Article |
| id | doaj-art-01dcc431ee1a4d65bf5a90616dae2510 |
| institution | DOAJ |
| issn | 1007-2683 |
| language | zho |
| publishDate | 2021-08-01 |
| publisher | Harbin University of Science and Technology Publications |
| record_format | Article |
| series | Journal of Harbin University of Science and Technology |
| spelling | doaj-art-01dcc431ee1a4d65bf5a90616dae25102025-08-20T03:02:28ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832021-08-0126049410110.15938/j.jhust.2021.04.013Few-shot Named Entity Ｒecognition for Medical TextQIN Jian0HOU Jian-xin1XIE Yi-ning2HE Yong-jun3School of Computer Science and Technology，Harbin University of Science and Technology，Harbin 150080，ChinaSchool of Computer Science and Technology，Harbin University of Science and Technology，Harbin 150080，ChinaSchool of Computer Science and Technology，Harbin University of Science and Technology，Harbin 150080，ChinaSchool of Computer Science and Technology，Harbin University of Science and Technology，Harbin 150080，ChinaAiming at the problem that medical text named entity recognition lacks sufficient labeled data，a newly named entity recognition deep neural network and data enhancement method is proposed. First of all，the Bert word vector is extended with pinyin and strokes of Chinese characters to make it contain more useful information. Then the named entity recognition model and the word segmentation model are jointly trained to enhance the model's ability to recognize entity boundaries. Finally，an improved data enhancement method is used to process the training data，which can increase the recognition effect of the model on named entities while avoiding overfitting of the model. The experimental results on the electronic medical record text provided by CCKS-2019 show that the proposed method can effectively improve the accuracy of named entity recognition in the case of small samples and the recognition rate can still be maintained without a significant decrease when the training data is reduced by half.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1998named entity recognitionfew-shotdata augmentationjoint trainingfeature fusion |
| spellingShingle | QIN Jian HOU Jian-xin XIE Yi-ning HE Yong-jun Few-shot Named Entity Ｒecognition for Medical Text Journal of Harbin University of Science and Technology named entity recognition few-shot data augmentation joint training feature fusion |
| title | Few-shot Named Entity Ｒecognition for Medical Text |
| title_full | Few-shot Named Entity Ｒecognition for Medical Text |
| title_fullStr | Few-shot Named Entity Ｒecognition for Medical Text |
| title_full_unstemmed | Few-shot Named Entity Ｒecognition for Medical Text |
| title_short | Few-shot Named Entity Ｒecognition for Medical Text |
| title_sort | few shot named entity recognition for medical text |
| topic | named entity recognition few-shot data augmentation joint training feature fusion |
| url | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1998 |
| work_keys_str_mv | AT qinjian fewshotnamedentityrecognitionformedicaltext AT houjianxin fewshotnamedentityrecognitionformedicaltext AT xieyining fewshotnamedentityrecognitionformedicaltext AT heyongjun fewshotnamedentityrecognitionformedicaltext |