Research on event extraction methods for medical

In response to the issue of fuzzy event argument boundaries in traditional Chinese medicine (TCM) event extraction, an event extraction model integrating local and global semantic features (EE-LGSF) was proposed, which combined convolutional neural networks, bidirectional long short-term memory netw...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuekun MA, Moxiao CUI
Format: Article
Language:zho
Published: Hebei University of Science and Technology 2025-04-01
Series:Journal of Hebei University of Science and Technology
Subjects:
Online Access:https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202502003?st=article_issue
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850282997878620160
author Yuekun MA
Moxiao CUI
author_facet Yuekun MA
Moxiao CUI
author_sort Yuekun MA
collection DOAJ
description In response to the issue of fuzzy event argument boundaries in traditional Chinese medicine (TCM) event extraction, an event extraction model integrating local and global semantic features (EE-LGSF) was proposed, which combined convolutional neural networks, bidirectional long short-term memory networks, and attention mechanisms to enhance the effectiveness of TCM event extraction. Firstly, multi-dimensional local feature information of the text was extracted by combining convolutional neural networks with different filter window sizes, while the global feature information of the text was captured using bidirectional long short-term memory networks. Secondly, on this basis, dynamic interaction between local and global information was achieved through gating mechanisms to enhance the ability of model to identify argument boundaries. Furthermore, a fuzzy span attention mechanism was introduced to dynamically adjust the attention range, thereby optimizing the decision-making process for argument spans. Finally, label prediction was performed using conditional random fields. The results indicate that the proposed model improves the F1 score by 3.0 to 11.0 percentage points on the TCM medical records data-set, demonstrating superior performance in addressing TCM event extraction issues compared to related models. The proposed model effectively leverages both local and global semantic information of the text, enhances the flexibility of span learning and improves the capability of the model to identify argument boundaries, thereby achieving better performance in TCM event extraction. It has reference value for the inheritance and development of TCM knowledge.
format Article
id doaj-art-4344f314062747beb46a9efbca1b58bf
institution OA Journals
issn 1008-1542
language zho
publishDate 2025-04-01
publisher Hebei University of Science and Technology
record_format Article
series Journal of Hebei University of Science and Technology
spelling doaj-art-4344f314062747beb46a9efbca1b58bf2025-08-20T01:47:51ZzhoHebei University of Science and TechnologyJournal of Hebei University of Science and Technology1008-15422025-04-0146214115010.7535/hbkd.2025yx02003b202502003Research on event extraction methods for medicalYuekun MA0Moxiao CUI1College of Artificial Intelligence, North China University of Science and Technology, Tangshan, Hebei 063210, ChinaCollege of Artificial Intelligence, North China University of Science and Technology, Tangshan, Hebei 063210, ChinaIn response to the issue of fuzzy event argument boundaries in traditional Chinese medicine (TCM) event extraction, an event extraction model integrating local and global semantic features (EE-LGSF) was proposed, which combined convolutional neural networks, bidirectional long short-term memory networks, and attention mechanisms to enhance the effectiveness of TCM event extraction. Firstly, multi-dimensional local feature information of the text was extracted by combining convolutional neural networks with different filter window sizes, while the global feature information of the text was captured using bidirectional long short-term memory networks. Secondly, on this basis, dynamic interaction between local and global information was achieved through gating mechanisms to enhance the ability of model to identify argument boundaries. Furthermore, a fuzzy span attention mechanism was introduced to dynamically adjust the attention range, thereby optimizing the decision-making process for argument spans. Finally, label prediction was performed using conditional random fields. The results indicate that the proposed model improves the F1 score by 3.0 to 11.0 percentage points on the TCM medical records data-set, demonstrating superior performance in addressing TCM event extraction issues compared to related models. The proposed model effectively leverages both local and global semantic information of the text, enhances the flexibility of span learning and improves the capability of the model to identify argument boundaries, thereby achieving better performance in TCM event extraction. It has reference value for the inheritance and development of TCM knowledge.https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202502003?st=article_issuenatural language processing; event extraction; traditional chinese medicine medical records; attention mechanism; convolutional neural network; dynamic fusion; span
spellingShingle Yuekun MA
Moxiao CUI
Research on event extraction methods for medical
Journal of Hebei University of Science and Technology
natural language processing; event extraction; traditional chinese medicine medical records; attention mechanism; convolutional neural network; dynamic fusion; span
title Research on event extraction methods for medical
title_full Research on event extraction methods for medical
title_fullStr Research on event extraction methods for medical
title_full_unstemmed Research on event extraction methods for medical
title_short Research on event extraction methods for medical
title_sort research on event extraction methods for medical
topic natural language processing; event extraction; traditional chinese medicine medical records; attention mechanism; convolutional neural network; dynamic fusion; span
url https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202502003?st=article_issue
work_keys_str_mv AT yuekunma researchoneventextractionmethodsformedical
AT moxiaocui researchoneventextractionmethodsformedical