检索结果-内蒙古大学图书馆

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Wen, Yi Wuhan Business Univ Wuhan 430056 Hubei Peoples R China

ISBN: (纸本)9798400718144

The balanced allocation of educational resources plays an important role in improving the quality of education and promoting educational equity. The current configuration models are difficult to understand resource information features and have limitations in automatic learning of features and resource classification. To improve the effectiveness of resource allocation and enhance the level of educational development, this article combines the BERT (bidirectional encoder representations from transformers) model to study self-adaptive allocation of educational resources. By using a brand new pre-trained language representation, the features of educational resources are extracted and interpreted, and the allocation scheme is optimized using a fitness function defined by heuristic algorithms. In the experimental analysis, this article uses the SVM (Support Vector Machine) model and CNN (Convolutional Neural Network) model as references to verify the application effect of the BERT model. The results showed that in the analysis of configuration effects, after training and optimizing the BERT model, the student-teacher ratio of various universities achieved significant improvement, with specific proportion values below 10.00. It can be concluded that self-adaptive allocation of educational resources based on the BERT model can help to achieve balanced development of educational resources and promote high-quality development of education.

关键词： Allocation of educational resources bidirectional encoder representations from transformers Self-adaptive mechanism Heuristic algorithm Resource classification

来源：评论

学校读者我要写书评

暂无评论

Cross-language Text Generation Using mBERT and XLM-R: English-Chinese Translation Task 24

Cross-language Text Generation Using mBERT and XLM-R: Englis...

引用

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Ma, Ying Wuhan Business Univ Wuhan 430056 Hubei Peoples R China

ISBN: (纸本)9798400718144

Traditional methods often require a large number of parallel corpora, that is, texts from one language and corresponding texts from another language. The acquisition and construction of this data is very expensive and time-consuming, which limits the application scope and feasibility of the model. This article used mBERT and XLM-R to solve the problem of relying on parallel corpora in traditional methods, and improved the quality of English-Chinese translation through the model's own multilingual representation ability. A publicly available parallel corpus of English-Chinese was collected for translation tasks, and the collected corpus was preprocessed with segmentation, punctuation, and other techniques. mBERT and XLM-R were used for English-Chinese translation respectively, and Ensemble method was adopted to weight and fuse the results of mBERT and XLM-R. BLEU (Bilingual Evaluation Understudy), METEOR (Metric for Evaluation of Translation with Explicit Ordering), and ROUGE (Recall-Oriented Understudy for Gisting Evaluation) were used to evaluate the quality of the translations. The average BLEU, average METEOR, and average ROUGE-L values of mBERT-XLM-R were 0.98, 0.97, and 0.98, respectively, according to the results. Therefore, mBERT and XLM-R working together may significantly enhance the quality of English-Chinese translation.

关键词： Cross-language Text Generation English-Chinese Translation Parallel Corpus bidirectional encoder representations from transformers

来源：评论

学校读者我要写书评

暂无评论

Intelligent Prescription-Generating Models of Traditional Chinese Medicine Based on Deep Learning

引用

World Journal of Traditional Chinese Medicine 2021年第3期7卷 361-369页

作者： Qing-Yang Shi Li-Zi Tan Lim Lian Seng Hui-Jun Wang Department of Traditional Chinese Medicine Tianjin University of Traditional Chinese MedicineTianjinChina Department of Traditional Chinese Medicine Malaysia Chinese Medical AssociationKuala LumpurMalaysia

Objective:This study aimed to construct an intelligent prescription-generating(IPG)model based on deep-learning natural language processing(NLP)technology for multiple prescriptions in Chinese *** and Methods:We selected the Treatise on Febrile Diseases and the Synopsis of Golden Chamber as basic datasets with EDA data augmentation,and the Yellow Emperor’s Canon of Internal Medicine,the Classic of the Miraculous Pivot,and the Classic on Medical Problems as supplementary datasets for *** selected the word-embedding model based on the Imperial Collection of Four,the bidirectional encoder representations from transformers(BERT)model based on the Chinese Wikipedia,and the robustly optimized BERT approach(RoBERTa)model based on the Chinese Wikipedia and a general *** addition,the BERT model was fine-tuned using the supplementary datasets to generate a Traditional Chinese Medicine-BERT *** IPG models were constructed based on the pretraining strategy and experiments were *** of precision,recall,and F1-score were used to assess the model *** on the trained models,we extracted and visualized the semantic features of some typical texts from treatise on febrile diseases and investigated the ***:Among all the trained models,the RoBERTa-large model performed the best,with a test set precision of 92.22%,recall of 86.71%,and F1-score of 89.38%and 10-fold cross-validation precision of 94.5%±2.5%,recall of 90.47%±4.1%,and F1-score of 92.38%±2.8%.The semantic feature extraction results based on this model showed that the model was intelligently stratified based on different meanings such that the within-layer’s patterns showed the associations of symptom–symptoms,disease–symptoms,and symptom–punctuations,while the between-layer’s patterns showed a progressive or dynamic symptom and disease ***:Deep-learning-based NLP technology significantly improves the performance of IPG mo

关键词： Ancient books of Chinese medicine bidirectional encoder representations from transformers deep learning intelligent prescription-generating models pretrained models

来源：评论

学校读者我要写书评

暂无评论

An Extensive Diagnosis System of Early Depression Symptoms using Machine Learning Algorithm 3

An Extensive Diagnosis System of Early Depression Symptoms u...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Anandkumar, K.M. Ajith, S. Bharathkumar, J. Hafeeluddeen, V.B.T. Easwari Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350343632

Suicidal deaths caused by depression have been an emerging crisis worldwide and is predicted by the World Health Organization (WHO) to accelerate to a much bigger scale. Seeking remedy for those affected by depression is a challenge posed by lack of accessibility to medical resources. For reasons such as mental health being a new topic to many, absence of immediate family/friends to openly discuss mental problems, and personal financial hardship to pursue therapy sessions. The proposed work of this research work aims to eliminate the mentioned barriers to seeking help, whilst acting as a companion tool to the user where every day self-assessment of emotions is encouraged. For immediate analysis, diagnosis namely Patient Health Questionnaire User (PHQ-9) is deployed to assess the individual. Inputs are concurrently monitored such as their activities and thoughts with the individual's consent and passed to a bidirectional encoder representations from transformers (BERT) model to detect early symptoms of depression. Remedial actions are suggested to the user to overcome depression and connect to a local mental health resource to aid the individual further. © 2023 IEEE.

关键词： bidirectional encoder representations from transformers Daily Journals Depression Detection Machine Learning Mental Health Natural Language Processing Physical Activity Monitoring Suicide Prevention

来源：评论

学校读者我要写书评

暂无评论

Advanced Multi-Task Reinforcement Learning Utilising Task-Adaptive Episodic Memory with Hypernetwork Integration 2

Advanced Multi-Task Reinforcement Learning Utilising Task-Ad...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prasanna Kumar, R. Prasanna Kumar, B.G. Sri Ramakrishna Prabhu, A. Upadhyay, Yash Teja, Nunna Vishnu Swamy, Penta Aravinda Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

In deep reinforcement learning, sampling ineffi-ciency is addressed by mimicking human learning which lever-Ages past experiences stored in the hippocampus. Integrating this idea, the proposed approach utilizes a task-conditioned hypernetwork retrieval network with MobileNet for feature extraction from past experiences. Furthermore, BERT was in-Tegrated for advanced natural language understanding, enabling our DRL agents to better interpret and act upon language-based tasks. This approach ensures dynamic adaptability and fosters a more efficient collaboration between retrieval and decision-making processes. Evaluation in MiniGrid demonstrates that the proposed method outperforms strong baselines, showing significant advancements in deep reinforcement learning with natural language processing capabilities. This advancement not only marks progress in sampling efficiency but also opens new avenues for multi-Task learning, paving the way for more intelligent, autonomous AI systems. © 2024 IEEE.

关键词： bidirectional encoder representations from transformers Deep Reinforcement Learning Episodic Memory Hypernetwork Multi-Task Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Recommender Systems in Mobile-assisted Language Learning (MALL): A Study of BERT-based Vocabulary Learning 3

Intelligent Recommender Systems in Mobile-assisted Language ...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Zhao, Yanmei Muhamad, Mohd Mokhtar Mustakim, Siti Salina Li, Wenling Wu, Xuanyi Wang, Aiping School of Foreign Languages Yuxi Normal University Yuxi China Universiti Putra Malaysia Faculty of Educational Studies Selangor Malaysia Universiti Putra Malaysia Faculty of Modern Languages and Communication Selangor Malaysia

ISBN: (纸本)9798350317022

With the popularity and development of mobile technology, mobile-assisted language learning (MALL) has gradually become essential to language learning. Intelligent recommender systems are increasingly important in MALL to improve learning efficiency and personalized experience. This paper explores how BERT (bidirectional encoder representations from transformers), a model with significant performance in natural language processing, can provide intelligent recommendations for vocabulary learning in MALL. First, it briefly introduces the basics of BERT and how it works. Then, it delves into how BERT can be utilized for data pre-processing, feature extraction, and model training in a MALL environment. In addition, this paper describes how to design an intelligent recommender system based on the user's learning history and preferences and proposes some ideas for integration with other technologies. This study suggests a new methodological framework by applying BERT technology in intelligent recommender systems within the MALL environment. Our research demonstrates how the deep learning capabilities of BERT can potentially enhance the personalized learning experience and efficiency of MALL systems. It provides a new perspective and theoretical foundation for applying deep learning technology in language learning, although further empirical research is required to validate these theoretical assumptions. Finally, an outlook on the future of BERT application in MALL and some suggestions are introduced. This paper aims to provide a reference framework for researchers and educators to understand and apply BERT in the field of MALL deeply. © 2023 IEEE.

关键词： bidirectional encoder representations from transformers intelligent recommender systems mobile-assisted language learning vocabulary learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Fake News Detection on Social Networks using Multimodal Approach of BERT and ResNet110

Automatic Fake News Detection on Social Networks using Multi...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Udayakumar, R. Yamsani, Nagendar Sajja, Sri Lavanya Ashok Kumar, Yaragani Lathakumari, K.R. Kalinga University Cs & It Chhattisgarh India Sr University School of Computer Science and Artificial Intelligence Warangal India Hyderabad India Hyderabad India Nitte Meenakshi Institute of Technology Bengaluru India

ISBN: (纸本)9798350313413

With the rapid development of online content-sharing and social media platforms has exploded for spreading fake news which create people trusting in unfavorable stories. This scenario allows to determine public opinion and produce chaos and panic through population. Therefore, detecting fake news has one of most significant topics which aims to identify a certain news is real or fake. The solution of fake news detection is split into three various classes such as content, social context and knowledge-based techniques. In this paper, a multimodal approach is proposed for detecting fake news for text and image, as well as classifying the news is real or fake. The bidirectional encoder representations from transformers (BERT) is used to extract text features and ResNet110 is used for image feature extraction. This model is estimated on Buzzfeed and ISOT dataset and attains better results using accuracy, precision, recall, specificity, and F1-score. The obtained result shows that the BERT+ResNet110 model achieves better accuracy of 98.51% on Buzzfeed dataset and 99.68% on ISOT dataset which ensures accurate detection compared to other existing methods like Random Forest (RF), Multi Support Vector Machine (MSVM) and Long Short-term Memory-Levy Flight (LSTM-LF). © 2023 IEEE.

关键词： bidirectional encoder representations from transformers Convolutional Neural Network Fake News Detection ResNet Tokenization

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned BERT Based Multilingual Model for Named Entity Recognition in Native Indian Languages

Fine-Tuned BERT Based Multilingual Model for Named Entity Re...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Mohan, G Bharathi Kumar, R Prasanna Elakkiya, R. Pendem, Mukhtesh Venkata Sri Sai Chennai India Dubai United Arab Emirates

ISBN: (纸本)9798350313413

Accurate recognition of named entities is essential in real-world applications such as information extraction, document classification, sentiment analysis, and machine *** fine-tuned BERT model demonstrates exceptional performance in multilingual NER tasks by leveraging language-specific opti-mization, cross-lingual transfer, and context understanding. In contrast, other models applied to multilingual data may exhibit limitations. The research utilizes the WikiAnn dataset, including languages like Tamil, Malayalam, Bengali, and Marathi, to train the fine-tuned BERT *** system achieved a precision of 95.3% and a recall of 94.8% for the Bengali language, outperforming the generic model used for Indian *** demonstrates superior accuracy and effectiveness in deciphering Bengali *** research provides a robust solution for accurate named entity recognition across multiple languages, benefiting real-world applications. © 2023 IEEE.

关键词： bidirectional encoder representations from transformers Machine Learning Named Entity Recognition Native Indian languages Natural Language Processing WikiAnn dataset

来源：评论

学校读者我要写书评

暂无评论

TRP-BERT: Discrimination of transient receptor potential (TRP) channels using contextual representations from deep bidirectional transformer based on BERT

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2021年 137卷 104821-104821页

作者： Shah, Syed Muazzam Ali Ou, Yu-Yen Yuan Ze Univ Dept Comp Sci & Engn Chungli 32003 Taiwan

Transient receptor potential (TRP) channels are non-selective cation channels that act as ion channels and are primarily found on the plasma membrane of numerous animal cells. These channels are involved in the physi-ology and pathophysiology of a wide variety of biological processes, including inhibition and progression of cancer, pain initiation, inflammation, regulation of pressure, thermoregulation, secretion of salivary fluid, and homeostasis of Ca2+ and Mg2+. Increasing evidences indicate that mutations in the gene encoding TRP channels play an essential role in a broad array of diseases. Therefore, these channels are becoming popular as potential drug targets for several diseases. The diversified role of these channels demands a prediction model to classify TRP channels from other channel proteins (non-TRP channels). Therefore, we presented an approach based on the Support Vector Machine (SVM) classifier and contextualized word embeddings from bidirectional encoder representations from transformers (BERT) to represent protein sequences. BERT is a deeply bidirectional lan-guage model and a neural network approach to Natural Language Processing (NLP) that achieves outstanding performance on various NLP tasks. We apply BERT to generate contextualized representations for every single amino acid in a protein sequence. Interestingly, these representations are context-sensitive and vary for the same amino acid appearing in different positions in the sequence. Our proposed method showed 80.00% sensitivity, 96.03% specificity, 95.47% accuracy, and a 0.56 Matthews correlation coefficient (MCC) for an independent test set. We suggest that our proposed method could effectively classify TRP channels from non-TRP channels and assist biologists in identifying new potential TRP channels.

关键词： TRP Transient receptor potential bidirectional encoder representations from transformers BERT Contextualized word embedding

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: Diverse ensemble classifier driven Email spam classification using multiple word embedding's with COCOB optimizer (Retracted Article)

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2024年第1期46卷 2941-2954页

作者： Vinitha, V. Sri Renuka, D. Karthika Bannari Amman Inst Technol Dept IT Sathyamangalam Tamil Nadu India PSG Coll Technol Dept IT Coimbatore Tamil Nadu India

Spam Email is a serious concern which can steal user's personal information and cause huge financial loss due to the increasing rate of internet users. Therefore, the demand for accurate spam filtering has become more sophisticated for the Email spam detection. In the existing techniques, it is difficult to intricate the relationship between words in the Email using certain word embedding techniques and learning rate tuning is one of the greatest challenges of stochastic optimization. To overcome this difficulty, the proposed framework uses diverse ensemble based Email spam classification by incorporating multiple word embedding's with Continuous Coin Betting optimizer. Word2Vec is used to produce the first set of 200D, next set of 200Dword embedding is produced by Glove and 768D is produced by using bidirectional encoder representations from transformers (BERT) respectively. After generating word embedding, then it is classified through diverse ensemble based classifier with base level classifier consists of Long Short Term Memory (LSTM) Networks, Gated Recurrent Unit (GRU) and Bi-directional Gated Recurrent Unit (Bi-GRU) and LSTM as Meta-classifier using COCOB optimizer. Experiments were conducted on 3 benchmark Email dataset and result shows that the proposed system outperforms well with a low false positive rate.

关键词： Word2Vec bidirectional encoder representations from transformers global vectors gated recurrent unit bidirectional gated recurrent unit long short term memory continuous coin betting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：