Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906349
Jian Zhang, Yunxiao Zu, Yong Zhang, Bin Hou
Network slicing is a key technology for addressing the issue of differentiated performance requirements of diversified services in mobile networks. Radio access network (RAN) slicing is a challenging task, as different levels of isolation requirements need to be considered. In this work, we investigate a network slicing problem for the downlink RAN of a cellular network and focus on three major 5G services, namely Ultra-Reliable Low-delay Communication (URLLC), and Large-scale Machine Type Communication (mMTC), Enhanced Mobile Broadband (eMBB). To be more practical, only the imperfect channel state information (CSI) is assumed to be available at the base station (BS) and allocate time-frequency resources dynamically to users through Lyapunov optimization, while ensuring slice isolation and setting different Quality-of-Service (QoS) requirements according to different slice types. Due to the scarcity of wireless resources, this paper aims to reduce resource usage. Simulation shows that this experiment is effective in ensuring QoS requirements, providing isolation and minimizing resource consumption.
{"title":"Dynamic RAN Slicing with Effective Isolation under Imperfect CSI","authors":"Jian Zhang, Yunxiao Zu, Yong Zhang, Bin Hou","doi":"10.1109/CCET55412.2022.9906349","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906349","url":null,"abstract":"Network slicing is a key technology for addressing the issue of differentiated performance requirements of diversified services in mobile networks. Radio access network (RAN) slicing is a challenging task, as different levels of isolation requirements need to be considered. In this work, we investigate a network slicing problem for the downlink RAN of a cellular network and focus on three major 5G services, namely Ultra-Reliable Low-delay Communication (URLLC), and Large-scale Machine Type Communication (mMTC), Enhanced Mobile Broadband (eMBB). To be more practical, only the imperfect channel state information (CSI) is assumed to be available at the base station (BS) and allocate time-frequency resources dynamically to users through Lyapunov optimization, while ensuring slice isolation and setting different Quality-of-Service (QoS) requirements according to different slice types. Due to the scarcity of wireless resources, this paper aims to reduce resource usage. Simulation shows that this experiment is effective in ensuring QoS requirements, providing isolation and minimizing resource consumption.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"97 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906345
Ka-Meng Siu, Ka‐Hou Chan, S. Im
The techniques of managing all Information Technology (IT) resources geared toward a company’s strategic goals and short-terms needs are generically known as IT management, which involves the decision making on the effective installations and coordination of hardware, software and data resources, human interventions, corporate policies and governance etc. To its brevity, the basic purpose of IT management is to add value to the organization through the use of technology so as to serve the best interest to the organization in operations. To get a better grasp of how to deal with today’s information technology, people must first understand the evolution of IT management. There are many traditional approaches to IT management that become increasingly important as current IT operations and systems established and managed by IT managers getting more and more vulnerable to failure in meeting goals. The purpose of this study is to examine the various evolutionary stages of IT management with an emphasis on software applications and systems.
{"title":"The Evolution and Practices of Current IT Management with a Focus on Applications with Data Management","authors":"Ka-Meng Siu, Ka‐Hou Chan, S. Im","doi":"10.1109/CCET55412.2022.9906345","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906345","url":null,"abstract":"The techniques of managing all Information Technology (IT) resources geared toward a company’s strategic goals and short-terms needs are generically known as IT management, which involves the decision making on the effective installations and coordination of hardware, software and data resources, human interventions, corporate policies and governance etc. To its brevity, the basic purpose of IT management is to add value to the organization through the use of technology so as to serve the best interest to the organization in operations. To get a better grasp of how to deal with today’s information technology, people must first understand the evolution of IT management. There are many traditional approaches to IT management that become increasingly important as current IT operations and systems established and managed by IT managers getting more and more vulnerable to failure in meeting goals. The purpose of this study is to examine the various evolutionary stages of IT management with an emphasis on software applications and systems.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124965621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906393
Li Guo, Zhongyue Chen, Xiaoping Chen
With the development of semantic segmentation, segmentation-based methods have yielded great success in detecting arbitrary-shaped texts. However, many existing text detection methods use binary discrete distributions to predict shrunk text instances, which cannot generate complete and accurate text bounding boxes. In this paper, we propose an arbitrary-shaped scene text detection method based on predicting Gaussian probability distance map of the complete text region, and this map can retain more text boundary information. Then, the boundary pixels are clustered into high-confidence text centers by a learnable post-processing and false positives are filtered out by pixel-level score maps. We also propose an adaptive channel enhancement module to improve the pixel-level segmentation accuracy. Experiments on three standard datasets, including CTW1500, Total-Text, and MSRA-TD500, demonstrate that the proposed method achieves great robustness and performance. The method obtains an F-measure of S2.S% on CTW1500 and S3.0% on MSRA-TD500.
{"title":"Arbitrary-Shaped Text Detection with Gaussian Probability Distance Distribution","authors":"Li Guo, Zhongyue Chen, Xiaoping Chen","doi":"10.1109/CCET55412.2022.9906393","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906393","url":null,"abstract":"With the development of semantic segmentation, segmentation-based methods have yielded great success in detecting arbitrary-shaped texts. However, many existing text detection methods use binary discrete distributions to predict shrunk text instances, which cannot generate complete and accurate text bounding boxes. In this paper, we propose an arbitrary-shaped scene text detection method based on predicting Gaussian probability distance map of the complete text region, and this map can retain more text boundary information. Then, the boundary pixels are clustered into high-confidence text centers by a learnable post-processing and false positives are filtered out by pixel-level score maps. We also propose an adaptive channel enhancement module to improve the pixel-level segmentation accuracy. Experiments on three standard datasets, including CTW1500, Total-Text, and MSRA-TD500, demonstrate that the proposed method achieves great robustness and performance. The method obtains an F-measure of S2.S% on CTW1500 and S3.0% on MSRA-TD500.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123518508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906387
Ning Tian, Yinghui Qiu
Virtual power plant is regarded as the ultimate configuration of energy internet and the terminal example of energy cloud. Firstly, this paper analyzes the value of virtual power plant to the current power energy system and classifies the control structure of Virtual Power Plant, and analyzes their characteristics; Then it introduces several important characteristics of virtual power plant and its special requirements for communication network. Secondly, it expounds the important technology of network slicing and the advantages of network slicing using virtualization technology to flexibly and differentially match resources according to business requirements. Then it introduces the architecture of network slicing and the isolation scheme of network slicing in different networks in detail. On this basis, this paper considers scheduling the network slices in the access network with virtual power plant according to the service priority, virtually isolating the services in the access network, resisting the attacks that may impact the communication system, and meeting the quality of service of the user side on the premise of reasonably regulating the network resources.
{"title":"Research on Network Slice Resource Scheduling in Virtual Power Plant","authors":"Ning Tian, Yinghui Qiu","doi":"10.1109/CCET55412.2022.9906387","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906387","url":null,"abstract":"Virtual power plant is regarded as the ultimate configuration of energy internet and the terminal example of energy cloud. Firstly, this paper analyzes the value of virtual power plant to the current power energy system and classifies the control structure of Virtual Power Plant, and analyzes their characteristics; Then it introduces several important characteristics of virtual power plant and its special requirements for communication network. Secondly, it expounds the important technology of network slicing and the advantages of network slicing using virtualization technology to flexibly and differentially match resources according to business requirements. Then it introduces the architecture of network slicing and the isolation scheme of network slicing in different networks in detail. On this basis, this paper considers scheduling the network slices in the access network with virtual power plant according to the service priority, virtually isolating the services in the access network, resisting the attacks that may impact the communication system, and meeting the quality of service of the user side on the premise of reasonably regulating the network resources.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"297 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133652746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906368
Qiuyu Xu, Xiaohong Shi, Qingshu Li, Wei Huang, Peng Yang
Computed Tomography (CT) is an authoritative verification standard for patients with Corona Virus Disease 2019 (COVID-19). Automatic detection of lung infection through CT is of great significance for epidemic prevention and control and prevention of cross-infection. The accuracy of existing lung CT image segmentation methods is not high, and due to the privacy protection measures of hospitals, the number of COVID-19 lung CT data sets is too small, which is prone to over-fitting during training. In this paper, we propose a qualitative mapping model for the diagnosis and localization of COVID-19 lesions. The binary image processed by U-net network is used as input, and lung CT is segmented as four attributes, and attribute diagnosis is carried out with the help of correlation matrix and transformation degree function. Experiments show that this method not only avoids the over-fitting risk of data sets, but also increases the robustness of data. Experiments also prove that this design has higher accuracy than the simple neural network learning.
{"title":"Attribute Analysis and Diagnosis of LUNG CT Images of COVID-19","authors":"Qiuyu Xu, Xiaohong Shi, Qingshu Li, Wei Huang, Peng Yang","doi":"10.1109/CCET55412.2022.9906368","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906368","url":null,"abstract":"Computed Tomography (CT) is an authoritative verification standard for patients with Corona Virus Disease 2019 (COVID-19). Automatic detection of lung infection through CT is of great significance for epidemic prevention and control and prevention of cross-infection. The accuracy of existing lung CT image segmentation methods is not high, and due to the privacy protection measures of hospitals, the number of COVID-19 lung CT data sets is too small, which is prone to over-fitting during training. In this paper, we propose a qualitative mapping model for the diagnosis and localization of COVID-19 lesions. The binary image processed by U-net network is used as input, and lung CT is segmented as four attributes, and attribute diagnosis is carried out with the help of correlation matrix and transformation degree function. Experiments show that this method not only avoids the over-fitting risk of data sets, but also increases the robustness of data. Experiments also prove that this design has higher accuracy than the simple neural network learning.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132635452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906389
Zibo Yi, Qingbo Wu, Jie Yu, Yongtao Tang, Xiaodong Liu, Long Peng, Jun Ma
In recent years, with the development of Tibetan language information technologies, the Internet Tibetan data is increasing year by year. Due to the need for the Tibetan input method and Tibetan error correction, Tibetan language prediction has become an urgent problem to be solved. At present, the challenges of Tibetan prediction are that the Tibetan syllable composition is complex, the vocabulary of Tibetan words which is composed of syllables is extremely large, and the Tibetan word separation technology is not mature. To solve the above problems, this paper proposes a Tibetan syllable prediction method based on a pre-trained cross-lingual language model using Tibetan syllables instead of Tibetan words as the token for prediction. The method uses the cross-lingual language model XLM-R and fine-tunes it using Tibetan news texts to make it more suitable for predicting Tibetan in the news domain. We conduct experiments on Tibetan syllable prediction for texts crawled on the Tibetan news website. The experiments show that the precision of our model for Tibetan text prediction is higher than that of the current n-gram methods.
{"title":"Tibetan Syllable Prediction with Pre-trained Cross-lingual Language Model","authors":"Zibo Yi, Qingbo Wu, Jie Yu, Yongtao Tang, Xiaodong Liu, Long Peng, Jun Ma","doi":"10.1109/CCET55412.2022.9906389","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906389","url":null,"abstract":"In recent years, with the development of Tibetan language information technologies, the Internet Tibetan data is increasing year by year. Due to the need for the Tibetan input method and Tibetan error correction, Tibetan language prediction has become an urgent problem to be solved. At present, the challenges of Tibetan prediction are that the Tibetan syllable composition is complex, the vocabulary of Tibetan words which is composed of syllables is extremely large, and the Tibetan word separation technology is not mature. To solve the above problems, this paper proposes a Tibetan syllable prediction method based on a pre-trained cross-lingual language model using Tibetan syllables instead of Tibetan words as the token for prediction. The method uses the cross-lingual language model XLM-R and fine-tunes it using Tibetan news texts to make it more suitable for predicting Tibetan in the news domain. We conduct experiments on Tibetan syllable prediction for texts crawled on the Tibetan news website. The experiments show that the precision of our model for Tibetan text prediction is higher than that of the current n-gram methods.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129242287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906347
Su Hang, Zhou Hanqing
This paper summarizes the disadvantages of regular word segmentation and statistical word segmentation, then a high performance Chinese word segmentation algorithm based on distributed character tree and unknown word recognition is proposed, which not only solves the defect of dictionary dependence in regular word segmentation, but also makes up for the lack of high time complexity in statistical word segmentation. The main innovations of the algorithm include: in the preprocessing stage, defining the distributed character tree and creating the feature dictionary; In the stage of word segmentation, the concept of word-formation skewness is defined, and the judgment formula of unknown word is proposed. The experimental results show that the new method has improved the accuracy and recall rate, which is applicable.
{"title":"Research on High Performance Word Segmentation Technology Based on Distributed Character Tree and Unknown Word Recognition","authors":"Su Hang, Zhou Hanqing","doi":"10.1109/CCET55412.2022.9906347","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906347","url":null,"abstract":"This paper summarizes the disadvantages of regular word segmentation and statistical word segmentation, then a high performance Chinese word segmentation algorithm based on distributed character tree and unknown word recognition is proposed, which not only solves the defect of dictionary dependence in regular word segmentation, but also makes up for the lack of high time complexity in statistical word segmentation. The main innovations of the algorithm include: in the preprocessing stage, defining the distributed character tree and creating the feature dictionary; In the stage of word segmentation, the concept of word-formation skewness is defined, and the judgment formula of unknown word is proposed. The experimental results show that the new method has improved the accuracy and recall rate, which is applicable.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131702606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906395
Jiayi Xu, Lei Yang, Meng Guo
During the COVID-19 pandemic, the demand for video calling and video conferencing is at peak and continues to grow. Integrating Augmented Reality (AR) with a regular video call can deliver a more interactive, immersive, and collaborative communication experience. This paper presents an AR video calling system that uses WebRTC protocol for establishing real-time video communication and uses AR SDK such as Google AR Core for adding AR features over the lively streaming video feed. To evaluate the performance and feasibility of the proposed AR video calling system, we implemented it on an Android mobile device and measured the relevant performance data, such as frame rate, CPU usage and network usage. The experimental results suggest that the proposed system is practicable and stable.
新冠肺炎疫情期间，视频通话和视频会议需求达到高峰并持续增长。将增强现实(AR)与常规视频通话集成可以提供更具互动性、沉浸式和协作性的通信体验。本文提出了一种AR视频通话系统，该系统使用WebRTC协议建立实时视频通信，并使用Google AR Core等AR SDK在实时流媒体视频馈送上添加AR功能。为了评估所提出的AR视频通话系统的性能和可行性，我们在Android移动设备上实现了该系统，并测量了相关的性能数据，如帧速率、CPU使用率和网络使用率。实验结果表明，该系统是可行的、稳定的。
{"title":"AR Mobile Video Calling System Based on WebRTC API","authors":"Jiayi Xu, Lei Yang, Meng Guo","doi":"10.1109/CCET55412.2022.9906395","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906395","url":null,"abstract":"During the COVID-19 pandemic, the demand for video calling and video conferencing is at peak and continues to grow. Integrating Augmented Reality (AR) with a regular video call can deliver a more interactive, immersive, and collaborative communication experience. This paper presents an AR video calling system that uses WebRTC protocol for establishing real-time video communication and uses AR SDK such as Google AR Core for adding AR features over the lively streaming video feed. To evaluate the performance and feasibility of the proposed AR video calling system, we implemented it on an Android mobile device and measured the relevant performance data, such as frame rate, CPU usage and network usage. The experimental results suggest that the proposed system is practicable and stable.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"290 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116240458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906355
Miaomiao Liu, Yuying Zhang, Dan Yao, Jingfeng Guo, Jing Chen
Aiming at the poor optimization performance of traditional Lion Swarm optimization algorithm, an improved algorithm is proposed based on Tent-map and differential evolution. Firstly, to address the problem of uneven population distribution and low efficiency in the later search stage, the chaotic sequence is introduced to improve the diversity and uniform traversal of the population so as to enhance the global search capability. Secondly, owing to the algorithm is prone to local optimum and unsatisfactory convergence accuracy, the lioness position update method is improved by the differential evolution to enhance its ability to jump out of the local optimum and boost the optimization accuracy. Experiments are carried out on 8 representative multi type benchmark functions, and compared with 4 optimization algorithms. Results show that the improved algorithm has higher convergence speed, training accuracy and stability.
{"title":"An Improved Lion Swarm Optimization Algorithm Based on Tent-map and Differential Evolution","authors":"Miaomiao Liu, Yuying Zhang, Dan Yao, Jingfeng Guo, Jing Chen","doi":"10.1109/CCET55412.2022.9906355","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906355","url":null,"abstract":"Aiming at the poor optimization performance of traditional Lion Swarm optimization algorithm, an improved algorithm is proposed based on Tent-map and differential evolution. Firstly, to address the problem of uneven population distribution and low efficiency in the later search stage, the chaotic sequence is introduced to improve the diversity and uniform traversal of the population so as to enhance the global search capability. Secondly, owing to the algorithm is prone to local optimum and unsatisfactory convergence accuracy, the lioness position update method is improved by the differential evolution to enhance its ability to jump out of the local optimum and boost the optimization accuracy. Experiments are carried out on 8 representative multi type benchmark functions, and compared with 4 optimization algorithms. Results show that the improved algorithm has higher convergence speed, training accuracy and stability.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126220660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906333
Jinshang Luo, Xinchun Zou, Mengshu Hou
Named Entity Recognition (NER) is a fundamental task in natural language processing. Compared with English NER, the difficulty of Chinese NER lies in word segmentation ambiguity and polysemy. Aiming at the issue, a novel character-word fusion Long Short-Term Memory (LSTM) model combined with the sentence-level attention mechanism (CWSA-LSTM) is proposed. Firstly, the method encodes the representations of characters and words through the pretrained models. The word information is incorporated into the character sequence by matching the potential word with a lexicon. Then the feature vectors are fed into the LSTM layer to learn contextual information. The attention mechanism is utilized to capture the tightness of the correlation in the sentence. Experiments on benchmark datasets demonstrate that CWSA-LSTM outperforms other state-of-the-art methods, and verify the effectiveness of character-word fusion. For the MSRA dataset, CWSA-LSTM achieves a 2.46% improvement in F1 score over baseline Lattice LSTM.
{"title":"A Novel Character-Word Fusion Chinese Named Entity Recognition Model Based on Attention Mechanism","authors":"Jinshang Luo, Xinchun Zou, Mengshu Hou","doi":"10.1109/CCET55412.2022.9906333","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906333","url":null,"abstract":"Named Entity Recognition (NER) is a fundamental task in natural language processing. Compared with English NER, the difficulty of Chinese NER lies in word segmentation ambiguity and polysemy. Aiming at the issue, a novel character-word fusion Long Short-Term Memory (LSTM) model combined with the sentence-level attention mechanism (CWSA-LSTM) is proposed. Firstly, the method encodes the representations of characters and words through the pretrained models. The word information is incorporated into the character sequence by matching the potential word with a lexicon. Then the feature vectors are fed into the LSTM layer to learn contextual information. The attention mechanism is utilized to capture the tightness of the correlation in the sentence. Experiments on benchmark datasets demonstrate that CWSA-LSTM outperforms other state-of-the-art methods, and verify the effectiveness of character-word fusion. For the MSRA dataset, CWSA-LSTM achieves a 2.46% improvement in F1 score over baseline Lattice LSTM.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126937230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：