Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware
Chinese nested named entity recognition(CNNER) is a challenging task due to the absence of natural delimiters in Chinese and the complexity of the nested structure.In this paper,we propose a novel boundary-aware layered neural model(BLNM) with segmentation attention for the CNNER task.To exploit som...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2023-01-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-1-213.pdf |
| _version_ | 1797845111432806400 |
|---|---|
| author | ZHANG Rujia, DAI Lu, GUO Peng, WANG Bang |
| author_facet | ZHANG Rujia, DAI Lu, GUO Peng, WANG Bang |
| author_sort | ZHANG Rujia, DAI Lu, GUO Peng, WANG Bang |
| collection | DOAJ |
| description | Chinese nested named entity recognition(CNNER) is a challenging task due to the absence of natural delimiters in Chinese and the complexity of the nested structure.In this paper,we propose a novel boundary-aware layered neural model(BLNM) with segmentation attention for the CNNER task.To exploit some semantic relation among adjacent characters,we first design a segmentation attention network to capture the potential word information and enhance character representation.Next,we model the nested structure with dynamically stacked Flat NER networks to detect entities in an inner to outer manner.We also design a boundary generative module to connect adjacent Flat NER layers,which can mark the boundary and position of detected entities and greatly alleviate the error propagation problem.Experiment results on ACE 2005 Chinese nested NE dataset show that the proposed model achieves superior performance than the state-of-the-art methods. |
| first_indexed | 2024-04-09T17:33:17Z |
| format | Article |
| id | doaj.art-1e65caaf4ba0497fad6f800318aad2aa |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:17Z |
| publishDate | 2023-01-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-1e65caaf4ba0497fad6f800318aad2aa2023-04-18T02:33:09ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2023-01-0150121322010.11896/jsjkx.211100257Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-awareZHANG Rujia, DAI Lu, GUO Peng, WANG Bang0School of Electronic Information and Communications,Huazhong University of Science and Technology,Wuhan 430074,ChinaChinese nested named entity recognition(CNNER) is a challenging task due to the absence of natural delimiters in Chinese and the complexity of the nested structure.In this paper,we propose a novel boundary-aware layered neural model(BLNM) with segmentation attention for the CNNER task.To exploit some semantic relation among adjacent characters,we first design a segmentation attention network to capture the potential word information and enhance character representation.Next,we model the nested structure with dynamically stacked Flat NER networks to detect entities in an inner to outer manner.We also design a boundary generative module to connect adjacent Flat NER layers,which can mark the boundary and position of detected entities and greatly alleviate the error propagation problem.Experiment results on ACE 2005 Chinese nested NE dataset show that the proposed model achieves superior performance than the state-of-the-art methods.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-1-213.pdfchinese nested named entity recognition|segmentation attention|boundary generative|layered neural network |
| spellingShingle | ZHANG Rujia, DAI Lu, GUO Peng, WANG Bang Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware Jisuanji kexue chinese nested named entity recognition|segmentation attention|boundary generative|layered neural network |
| title | Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware |
| title_full | Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware |
| title_fullStr | Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware |
| title_full_unstemmed | Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware |
| title_short | Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware |
| title_sort | chinese nested named entity recognition algorithm based on segmentation attention andboundary aware |
| topic | chinese nested named entity recognition|segmentation attention|boundary generative|layered neural network |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-1-213.pdf |
| work_keys_str_mv | AT zhangrujiadailuguopengwangbang chinesenestednamedentityrecognitionalgorithmbasedonsegmentationattentionandboundaryaware |