A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM
In order to improve disambiguation accuracy of biomedical abbreviations， a semi-supervised abbreviation disambiguation method based on asymmetric convolutional neural networks and bidirectional long short term memory networks is proposed. Abbreviation is viewed as center. Morphology information， par...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin University of Science and Technology Publications
2022-10-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849417278912724992 |
|---|---|
| author | ZHANG Chun-xiang PANG Shu-yang GAO Xue-yao |
| author_facet | ZHANG Chun-xiang PANG Shu-yang GAO Xue-yao |
| author_sort | ZHANG Chun-xiang |
| collection | DOAJ |
| description | In order to improve disambiguation accuracy of biomedical abbreviations， a semi-supervised abbreviation disambiguation method based on asymmetric convolutional neural networks and bidirectional long short term memory networks is proposed. Abbreviation is viewed as center. Morphology information， part of speech and semantic information from four adjacent lexical units are extracted as disambiguation features. Training corpus is extended by using Xgboost algorithm and LightGBM algorithm， and then expanded training corpus is input into this model. Asymmetric convolutional neural networks (ACNN) and bidirectional long short-term memory (Bi-LSTM) networks are utilized to extract features. Softmax function is applied to semantic classification. MSH corpus is adopted to optimize this model and test its disambiguation performance. Experimental results show that the proposed model can effectively improve disambiguation accuracy of abbreviations by using only a small amount of annotated corpus. |
| format | Article |
| id | doaj-art-b8f0b6b3e7dd4af4992c8f77ad643391 |
| institution | Kabale University |
| issn | 1007-2683 |
| language | zho |
| publishDate | 2022-10-01 |
| publisher | Harbin University of Science and Technology Publications |
| record_format | Article |
| series | Journal of Harbin University of Science and Technology |
| spelling | doaj-art-b8f0b6b3e7dd4af4992c8f77ad6433912025-08-20T03:32:54ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-10-012705303710.15938/j.jhust.2022.05.005A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM ZHANG Chun-xiang0PANG Shu-yang1GAO Xue-yao2School 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， ChinaIn order to improve disambiguation accuracy of biomedical abbreviations， a semi-supervised abbreviation disambiguation method based on asymmetric convolutional neural networks and bidirectional long short term memory networks is proposed. Abbreviation is viewed as center. Morphology information， part of speech and semantic information from four adjacent lexical units are extracted as disambiguation features. Training corpus is extended by using Xgboost algorithm and LightGBM algorithm， and then expanded training corpus is input into this model. Asymmetric convolutional neural networks (ACNN) and bidirectional long short-term memory (Bi-LSTM) networks are utilized to extract features. Softmax function is applied to semantic classification. MSH corpus is adopted to optimize this model and test its disambiguation performance. Experimental results show that the proposed model can effectively improve disambiguation accuracy of abbreviations by using only a small amount of annotated corpus.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2135abbreviationxgboostlightgbmdisambiguation featureasymmetric convolution neural networkbidirectional long short-term memory |
| spellingShingle | ZHANG Chun-xiang PANG Shu-yang GAO Xue-yao A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM Journal of Harbin University of Science and Technology abbreviation xgboost lightgbm disambiguation feature asymmetric convolution neural network bidirectional long short-term memory |
| title | A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM |
| title_full | A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM |
| title_fullStr | A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM |
| title_full_unstemmed | A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM |
| title_short | A Semi-Supervised Abbreviation Disambiguation Method Based on ACNN and Bi-LSTM |
| title_sort | semi supervised abbreviation disambiguation method based on acnn and bi lstm |
| topic | abbreviation xgboost lightgbm disambiguation feature asymmetric convolution neural network bidirectional long short-term memory |
| url | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2135 |
| work_keys_str_mv | AT zhangchunxiang asemisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm AT pangshuyang asemisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm AT gaoxueyao asemisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm AT zhangchunxiang semisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm AT pangshuyang semisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm AT gaoxueyao semisupervisedabbreviationdisambiguationmethodbasedonacnnandbilstm |