Named Entity Recognition(NER)is one of the fundamental tasks in Natural Language Processing(NLP),which aims to locate,extract,and classify named entities into a predefined category such as person,organization and loca...Named Entity Recognition(NER)is one of the fundamental tasks in Natural Language Processing(NLP),which aims to locate,extract,and classify named entities into a predefined category such as person,organization and location.Most of the earlier research for identifying named entities relied on using handcrafted features and very large knowledge resources,which is time consuming and not adequate for resource-scarce languages such as Arabic.Recently,deep learning achieved state-of-the-art performance on many NLP tasks including NER without requiring hand-crafted features.In addition,transfer learning has also proven its efficiency in several NLP tasks by exploiting pretrained language models that are used to transfer knowledge learned from large-scale datasets to domain-specific tasks.Bidirectional Encoder Representation from Transformer(BERT)is a contextual language model that generates the semantic vectors dynamically according to the context of the words.BERT architecture relay on multi-head attention that allows it to capture global dependencies between words.In this paper,we propose a deep learning-based model by fine-tuning BERT model to recognize and classify Arabic named entities.The pre-trained BERT context embeddings were used as input features to a Bidirectional Gated Recurrent Unit(BGRU)and were fine-tuned using two annotated Arabic Named Entity Recognition(ANER)datasets.Experimental results demonstrate that the proposed model outperformed state-of-the-art ANER models achieving 92.28%and 90.68%F-measure values on the ANERCorp dataset and the merged ANERCorp and AQMAR dataset,respectively.展开更多
文本情感分类的核心问题是如何有效地表示文本的情感语义,然而,目前的大多数方法只考虑到了文本内容中的情感语义,忽略了与文本内容相关的用户信息以及文本内容所描述的产品信息。已有的包含用户和产品信息方法也存在着以下两个问题:(1...文本情感分类的核心问题是如何有效地表示文本的情感语义,然而,目前的大多数方法只考虑到了文本内容中的情感语义,忽略了与文本内容相关的用户信息以及文本内容所描述的产品信息。已有的包含用户和产品信息方法也存在着以下两个问题:(1)不能有效地表示用户和产品信息,而且模型复杂度过高导致训练速度满。(2)文本情感语义表示模型过于简单,不能有效地表示文本中的上下文语义信息。针对以上两个问题,提出了相应的解决方案:(1)针对用户和产品的评价数据,利用奇异值分解(Singular Value Decomposition,SVD)的方法得到用户和产品的语义准确的先验信息,同时避免了用户和产品信息等相关参数的训练,缓解了模型复杂度高的问题。(2)利用双向的门循环单元(GRU)模型代替原有的简单模型,更加有效地结合了文本中的上下文语义信息。实验结果表明:相比传统的文本分类方法,提出的方法有更好的分类效果,在部分实验数据中达到了最好的分类准确度。同时模型的训练速度也得到了提升。展开更多
Oral Squamous Cell Carcinoma(OSCC)is a type of Head and Neck Squamous Cell Carcinoma(HNSCC)and it should be diagnosed at early stages to accomplish efficient treatment,increase the survival rate,and reduce death rate....Oral Squamous Cell Carcinoma(OSCC)is a type of Head and Neck Squamous Cell Carcinoma(HNSCC)and it should be diagnosed at early stages to accomplish efficient treatment,increase the survival rate,and reduce death rate.Histopathological imaging is a wide-spread standard used for OSCC detection.However,it is a cumbersome process and demands expert’s knowledge.So,there is a need exists for automated detection ofOSCC using Artificial Intelligence(AI)and Computer Vision(CV)technologies.In this background,the current research article introduces Improved Slime Mould Algorithm with Artificial Intelligence Driven Oral Cancer Classification(ISMA-AIOCC)model on Histopathological images(HIs).The presented ISMA-AIOCC model is aimed at identification and categorization of oral cancer using HIs.At the initial stage,linear smoothing filter is applied to eradicate the noise from images.Besides,MobileNet model is employed to generate a useful set of feature vectors.Then,Bidirectional Gated Recurrent Unit(BGRU)model is exploited for classification process.At the end,ISMA algorithm is utilized to fine tune the parameters involved in BGRU model.Moreover,ISMA algorithm is created by integrating traditional SMA and ChaoticOppositional Based Learning(COBL).The proposed ISMA-AIOCC model was validated for performance using benchmark dataset and the results pointed out the supremacy of ISMA-AIOCC model over other recent approaches.展开更多
基金funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University through the Graduate Students Research Support Program.
文摘Named Entity Recognition(NER)is one of the fundamental tasks in Natural Language Processing(NLP),which aims to locate,extract,and classify named entities into a predefined category such as person,organization and location.Most of the earlier research for identifying named entities relied on using handcrafted features and very large knowledge resources,which is time consuming and not adequate for resource-scarce languages such as Arabic.Recently,deep learning achieved state-of-the-art performance on many NLP tasks including NER without requiring hand-crafted features.In addition,transfer learning has also proven its efficiency in several NLP tasks by exploiting pretrained language models that are used to transfer knowledge learned from large-scale datasets to domain-specific tasks.Bidirectional Encoder Representation from Transformer(BERT)is a contextual language model that generates the semantic vectors dynamically according to the context of the words.BERT architecture relay on multi-head attention that allows it to capture global dependencies between words.In this paper,we propose a deep learning-based model by fine-tuning BERT model to recognize and classify Arabic named entities.The pre-trained BERT context embeddings were used as input features to a Bidirectional Gated Recurrent Unit(BGRU)and were fine-tuned using two annotated Arabic Named Entity Recognition(ANER)datasets.Experimental results demonstrate that the proposed model outperformed state-of-the-art ANER models achieving 92.28%and 90.68%F-measure values on the ANERCorp dataset and the merged ANERCorp and AQMAR dataset,respectively.
文摘文本情感分类的核心问题是如何有效地表示文本的情感语义,然而,目前的大多数方法只考虑到了文本内容中的情感语义,忽略了与文本内容相关的用户信息以及文本内容所描述的产品信息。已有的包含用户和产品信息方法也存在着以下两个问题:(1)不能有效地表示用户和产品信息,而且模型复杂度过高导致训练速度满。(2)文本情感语义表示模型过于简单,不能有效地表示文本中的上下文语义信息。针对以上两个问题,提出了相应的解决方案:(1)针对用户和产品的评价数据,利用奇异值分解(Singular Value Decomposition,SVD)的方法得到用户和产品的语义准确的先验信息,同时避免了用户和产品信息等相关参数的训练,缓解了模型复杂度高的问题。(2)利用双向的门循环单元(GRU)模型代替原有的简单模型,更加有效地结合了文本中的上下文语义信息。实验结果表明:相比传统的文本分类方法,提出的方法有更好的分类效果,在部分实验数据中达到了最好的分类准确度。同时模型的训练速度也得到了提升。
基金The work is supported by the Ministry of Science and Higher Education of the Russian Federation(Government Order FENU-2020-0022).
文摘Oral Squamous Cell Carcinoma(OSCC)is a type of Head and Neck Squamous Cell Carcinoma(HNSCC)and it should be diagnosed at early stages to accomplish efficient treatment,increase the survival rate,and reduce death rate.Histopathological imaging is a wide-spread standard used for OSCC detection.However,it is a cumbersome process and demands expert’s knowledge.So,there is a need exists for automated detection ofOSCC using Artificial Intelligence(AI)and Computer Vision(CV)technologies.In this background,the current research article introduces Improved Slime Mould Algorithm with Artificial Intelligence Driven Oral Cancer Classification(ISMA-AIOCC)model on Histopathological images(HIs).The presented ISMA-AIOCC model is aimed at identification and categorization of oral cancer using HIs.At the initial stage,linear smoothing filter is applied to eradicate the noise from images.Besides,MobileNet model is employed to generate a useful set of feature vectors.Then,Bidirectional Gated Recurrent Unit(BGRU)model is exploited for classification process.At the end,ISMA algorithm is utilized to fine tune the parameters involved in BGRU model.Moreover,ISMA algorithm is created by integrating traditional SMA and ChaoticOppositional Based Learning(COBL).The proposed ISMA-AIOCC model was validated for performance using benchmark dataset and the results pointed out the supremacy of ISMA-AIOCC model over other recent approaches.