CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition
Chinese medical named entity recognition (NER) is a fundamental task in Chinese medical natural language processing, aiming to recognize Chinese medical entities within unstructured medical texts. However, it poses significant challenges mainly due to the extensive usage of medical terms in Chinese...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023079008 |
| _version_ | 1797646519919181824 |
|---|---|
| author | Yinlong Xiao Zongcheng Ji Jianqiang Li Qing Zhu |
| author_facet | Yinlong Xiao Zongcheng Ji Jianqiang Li Qing Zhu |
| author_sort | Yinlong Xiao |
| collection | DOAJ |
| description | Chinese medical named entity recognition (NER) is a fundamental task in Chinese medical natural language processing, aiming to recognize Chinese medical entities within unstructured medical texts. However, it poses significant challenges mainly due to the extensive usage of medical terms in Chinese medical texts. Although previous studies have made attempts to incorporate lexical or radical knowledge in order to improve the comprehension of medical texts, these studies either focus solely on one of these aspects or utilize a basic concatenation operation to combine these features, which fails to fully utilize the potential of lexical and radical knowledge. In this paper, we propose a novel Cascaded LAttice-and-Radical Transformer (CLART) network to exploit both lexical and radical information for Chinese medical NER. Specifically, given a sentence, a medical lexicon, and a radical dictionary, we first construct a flat lattice (i.e., character-word sequence) for the sentence and radical components of each Chinese character through word matching and radical parsing, respectively. We then employ a lattice Transformer module to capture the dense interactions between characters and matched words, facilitating the enhanced utilization of lexical knowledge. Subsequently, we design a radical Transformer module to model the dense interactions between the lattice and radical features, facilitating better fusion of the lexical and radical knowledge. Finally, we feed the updated lattice-and-radical-aware character representations into a Conditional Random Fields (CRF) decoder to obtain the predicted labels. Experimental results conducted on two publicly available Chinese medical NER datasets show the effectiveness of the proposed method. |
| first_indexed | 2024-03-11T15:02:49Z |
| format | Article |
| id | doaj.art-71cacba8e97b412990de9e016d48aa37 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-11T15:02:49Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-71cacba8e97b412990de9e016d48aa372023-10-30T06:07:02ZengElsevierHeliyon2405-84402023-10-01910e20692CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognitionYinlong Xiao0Zongcheng Ji1Jianqiang Li2Qing Zhu3Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaPAII Inc., CA 94087, United States of AmericaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Corresponding author.Chinese medical named entity recognition (NER) is a fundamental task in Chinese medical natural language processing, aiming to recognize Chinese medical entities within unstructured medical texts. However, it poses significant challenges mainly due to the extensive usage of medical terms in Chinese medical texts. Although previous studies have made attempts to incorporate lexical or radical knowledge in order to improve the comprehension of medical texts, these studies either focus solely on one of these aspects or utilize a basic concatenation operation to combine these features, which fails to fully utilize the potential of lexical and radical knowledge. In this paper, we propose a novel Cascaded LAttice-and-Radical Transformer (CLART) network to exploit both lexical and radical information for Chinese medical NER. Specifically, given a sentence, a medical lexicon, and a radical dictionary, we first construct a flat lattice (i.e., character-word sequence) for the sentence and radical components of each Chinese character through word matching and radical parsing, respectively. We then employ a lattice Transformer module to capture the dense interactions between characters and matched words, facilitating the enhanced utilization of lexical knowledge. Subsequently, we design a radical Transformer module to model the dense interactions between the lattice and radical features, facilitating better fusion of the lexical and radical knowledge. Finally, we feed the updated lattice-and-radical-aware character representations into a Conditional Random Fields (CRF) decoder to obtain the predicted labels. Experimental results conducted on two publicly available Chinese medical NER datasets show the effectiveness of the proposed method.http://www.sciencedirect.com/science/article/pii/S2405844023079008Chinese medical named entity recognitionLattice structureRadical informationAttention mechanismTransformer |
| spellingShingle | Yinlong Xiao Zongcheng Ji Jianqiang Li Qing Zhu CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition Heliyon Chinese medical named entity recognition Lattice structure Radical information Attention mechanism Transformer |
| title | CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition |
| title_full | CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition |
| title_fullStr | CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition |
| title_full_unstemmed | CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition |
| title_short | CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition |
| title_sort | clart a cascaded lattice and radical transformer network for chinese medical named entity recognition |
| topic | Chinese medical named entity recognition Lattice structure Radical information Attention mechanism Transformer |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023079008 |
| work_keys_str_mv | AT yinlongxiao clartacascadedlatticeandradicaltransformernetworkforchinesemedicalnamedentityrecognition AT zongchengji clartacascadedlatticeandradicaltransformernetworkforchinesemedicalnamedentityrecognition AT jianqiangli clartacascadedlatticeandradicaltransformernetworkforchinesemedicalnamedentityrecognition AT qingzhu clartacascadedlatticeandradicaltransformernetworkforchinesemedicalnamedentityrecognition |