检索结果-内蒙古大学图书馆

Enhanced Topic-Aware Summarization Using Statistical Graph Neural Networks

Computers, Materials & Continua 2024年第8期80卷 3221-3242页

作者： Ayesha Khaliq Salman Afsar Awan Fahad Ahmad Muhammad Azam Zia Muhammad Zafar Iqbal Department of Computer Science University of Agriculture FaisalabadFaisalabadPunjab37300Pakistan School of Computing Faculty of TechnologyUniversity of PortsmouthSouthseaPortsmouthPO12UPUK Department of Mathematics and Statistics University of Agriculture FaisalabadFaisalabadPunjab37300Pakistan

The rapid expansion of online content and big data has precipitated an urgent need for efficient summarization techniques to swiftly comprehend vast textual documents without compromising their original *** approaches in Extractive Text Summarization(ETS)leverage the modeling of inter-sentence relationships,a task of paramount importance in producing coherent *** study introduces an innovative model that integrates Graph Attention Networks(GATs)with Transformer-based bidirectional encoder Representa-tions from transformers(BERT)and Latent Dirichlet Allocation(LDA),further enhanced by Term Frequency-Inverse Document Frequency(TF-IDF)values,to improve sentence selection by capturing comprehensive topical *** approach constructs a graph with nodes representing sentences,words,and topics,thereby elevating the interconnectivity and enabling a more refined understanding of text *** model is stretched to Multi-Document Summarization(MDS)from Single-Document Summarization,offering significant improvements over existing models such as THGS-GMM and Topic-GraphSum,as demonstrated by empirical evaluations on benchmark news datasets like Cable News Network(CNN)/Daily Mail(DM)and *** results consistently demonstrate superior performance,showcasing the model’s robustness in handling complex summarization tasks across single and multi-document *** research not only advances the integration of BERT and LDA within a GATs but also emphasizes our model’s capacity to effectively manage global information and adapt to diverse summarization challenges.

关键词： Summarization graph attention network bidirectional encoder representations from transformers Latent Dirichlet Allocation term frequency-inverse document frequency

来源：评论

学校读者我要写书评

暂无评论

TRCaptionNet: A novel and accurate deep Turkish image captioning model with vision transformer based image encoders and deep linguistic text decoders

引用

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES 2023年第6期31卷 1079-1098页

作者： Yildiz, Serdar Memis, Abbas Varli, Songul Yildiz Tech Univ Fac Elect & Elect Engn Dept Comp Engn Istanbul Turkiye Hlth Inst Turkiye Istanbul Turkiye TUBITAK BILGEM Kocaeli Turkiye

Image captioning is known as a fundamental computer vision task aiming to figure out and describe what is happening in an image or image region. Through an image captioning process, it is ensured to describe and define the actions and the relations of the objects within the images. In this manner, the contents of the images can be understood and interpreted automatically by visual computing systems. In this paper, we proposed the TRCaptionNet a novel deep learning-based Turkish image captioning (TIC) model for the automatic generation of Turkish captions. The model we propose essentially consists of a basic image encoder, a feature projection module based on vision transformers, and a text decoder. In the first stage, the system encodes the input images via the CLIP (contrastive language-image pretraining) image encoder. The CLIP image features are then passed through a vision transformer and the final image features to be linked with the textual features are obtained. In the last stage, a deep text decoder exploiting a BERT (bidirectional encoder representations from transformers) based model is used to generate the image cations. Furthermore, unlike the related works, a natural language-based linguistic model called NLLB (No Language Left Behind) was employed to produce Turkish captions from the original English captions. Extensive performance evaluation studies were carried out and widely known image captioning quantification metrics such as BLEU, METEOR, ROUGE-L, and CIDEr were measured for the proposed model. Within the scope of the experiments, quite successful results were observed on MS COCO and Flickr30K datasets, two known and prominent datasets in this field. As a result of the comparative performance analysis by taking the existing reports in the current literature on TIC into consideration, it was witnessed that the proposed model has superior performance and outperforms the related works on TIC so far. Project details and demo links of TRCaptionNet wil

关键词： Image captioning image understanding Turkish image captioning contrastive language-image pretraining bidirectional encoder representations from transformers image and natural language processing

来源：评论

学校读者我要写书评

暂无评论

The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review

引用

JMIR MEDICAL INFORMATICS 2024年 12卷 e53787页

作者： Preiksaitis, Carl Ashenburg, Nicholas Bunney, Gabrielle Chu, Andrew Kabeer, Rana Riley, Fran Ribeira, Ryan Rose, Christian Stanford Univ Sch Med Dept Emergency Med 900 Welch Rd Suite 350 Palo Alto CA 94304 USA

Background: Artificial intelligence (AI), more specifically large language models (LLMs), holds significant potential in revolutionizing emergency care delivery by optimizing clinical workflows and enhancing the quality of decision-making. Although enthusiasm for integrating LLMs into emergency medicine (EM) is growing, the existing literature is characterized by a disparate collection of individual studies, conceptual analyses, and preliminary implementations. Given these complexities and gaps in understanding, a cohesive framework is needed to comprehend the existing body of knowledge on the application of LLMs in Objective: Given the absence of a comprehensive framework for exploring the roles of LLMs in EM, this scoping review aims to systematically map the existing literature on LLMs' potential applications within EM and identify directions for future research. Addressing this gap will allow for informed advancements in the field. Methods: Using PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) criteria, we searched Ovid MEDLINE, Embase, Web of Science, and Google Scholar for papers published between January 2018 and August 2023 that discussed LLMs' use in EM. We excluded other forms of AI. A total of 1994 unique titles and abstracts were screened, and each full-text paper was independently reviewed by 2 authors. Data were abstracted independently, and 5 authors performed a collaborative quantitative and qualitative synthesis of the data. Results: A total of 43 papers were included. Studies were predominantly from 2022 to 2023 and conducted in the United States and China. We uncovered four major themes: (1) clinical decision-making and support was highlighted as a pivotal area, with LLMs playing a substantial role in enhancing patient care, notably through their application in real-time triage, allowing early recognition of patient urgency;(2) efficiency, workflow, and information management demonstrat

关键词： large language model LLM emergency medicine clinical decision support workflow efficiency medical education artificial intelligence AI natural language processing NLP AI literacy ChatGPT Bard Pathways Language Model Med-PaLM bidirectional encoder representations from transformers BERT generative pretrained transformer GPT United States US China scoping review Preferred Reporting Items for Systematic Reviews and Meta-Analyses PRISMA decision support workflow efficiency risk ethics education communication medical training physician health literacy emergency care

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing for Automated Classification of Qualitative Data from Interviews of Patients With Cancer

引用

VALUE IN HEALTH 2022年第12期25卷 1995-2002页

作者： Fang, Chao Markuzon, Natasha Patel, Nikunj Rueda, Juan-David AstraZeneca Oncol Biometr ML AI 760 Winter St Waltham MA 02451 USA AstraZeneca US Med Affairs Gaithersburg MD USA AstraZeneca Oncol Market Access & Pricing Gaithersburg MD USA

Objectives: This study sought to explore the use of novel natural language processing (NLP) methods for classifying unstructured, qualitative textual data from interviews of patients with cancer to identify patient-reported symptoms and impacts on quality of life. Methods: We tested the ability of 4 NLP models to accurately classify text from interview transcripts as "symptom," "quality of life impact" and "other." Interview data sets from patients with hepatocellular carcinoma (HCC) (n = 25), biliary tract cancer (BTC) (n = 23), and gastric cancer (n = 24) were used. Models were cross-validated with transcript subsets designated for training, validation, and testing. Multiclass classification performance of the 4 models was evaluated at paragraph and sentence level using the HCC testing data set and analyzed by the one-versus-rest technique quantified by the receiver operating characteristic area under the curve (ROC AUC) score. Results: NLP models accurately classified multiclass text from patient interviews. The bidirectional encoder representations from transformers model generally outperformed all other models at paragraph and sentence level. The highest predictive performance of the bidirectional encoder representations from transformers model was observed using the HCC data set to train and BTC data set to test (mean ROC AUC, 0.940 [SD 0.028]), with similarly high predictive performance using balanced and imbalanced training data sets from BTC and gastric cancer populations. Conclusions: NLP models were accurate in predicting multiclass classification of text from interviews of patients with cancer, with most surpassing 0.9 ROC AUC at paragraph level. NLP may be a useful tool for scaling up processing of patient interviews in clinical studies and, thus, could serve to facilitate patient input into drug development and improving patient care.

关键词： bidirectional encoder representations from transformers natural language processing patient interviews patient-reported outcomes

来源：评论

学校读者我要写书评

暂无评论

Exploring Public Emotions on Obesity During the COVID-19Pandemic Using Sentiment Analysis and Topic Modeling:Cross-Sectional Study

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2024年 26卷 e52142页

作者： Correia, Jorge Cesar Ahmad, Sarmad Shaharyar Waqas, Ahmed Meraj, Hafsa Pataky, Zoltan Univ Hosp Geneva WHO Collaborating Ctr Unit Therapeut Patient Educ Chemin Venel 7 CH-1206 Geneva Switzerland Univ Geneva Chemin Venel 7 CH-1206 Geneva Switzerland Liverpool Hope Univ Sch Math Comp Sci & Engn Liverpool England Univ Liverpool Inst Populat Hlth Dept Primary Care & Mental Hlth Liverpool England Greater Manchester Mental Hlth NHS Fdn Trust Salford England

Background: Obesity is a chronic, multifactorial, and relapsing disease, affecting people of all ages worldwide, and is directly related to multiple complications. Understanding public attitudes and perceptions toward obesity is essential for developing effective health policies, prevention strategies, and treatment approaches. Objective: This study investigated the sentiments of the general public, celebrities, and important organizations regarding obesity using social media data, specifically from Twitter (subsequently rebranded as X).Methods: The study analyzes a dataset of 53,414 tweets related to obesity posted on Twitter during the COVID-19 pandemic, from April 2019 to December 2022. Sentiment analysis was performed using the XLM-RoBERTa-base model, and topic modeling was conducted using the BERTopic library. Results: The analysis revealed that tweets regarding obesity were predominantly negative. Spikes in Twitter activity correlated with significant political events, such as the exchange of obesity-related comments between US politicians and criticism of theUnited Kingdom's obesity campaign. Topic modeling identified 243 clusters representing various obesity-related topics, such as childhood obesity;the US President's obesity struggle;COVID-19 vaccinations;the UK government's obesity campaign;body shaming;racism and high obesity rates among Black American people;smoking, substance abuse, and alcohol consumption among people with obesity;environmental risk factors;and surgical treatments. Conclusions: Twitter serves as a valuable source for understanding obesity-related sentiments and attitudes among the public, celebrities, and influential organizations. Sentiments regarding obesity were predominantly negative. Negative portrayals of obesity by influential politicians and celebrities were shown to contribute to negative public sentiments, which can have adverse effects on public health. It is essential for public figures to be mindful of their impact on publ

关键词： obesity Twitter infodemic attitude opinion perception perspective obese weight overweight social media tweet sentiment topic modeling BERT bidirectional encoder representations from transformers NLP natural language processing generalpublic celebrities

来源：评论

学校读者我要写书评

暂无评论

CGDGMDA-Net: discovering microbe-disease and drug associations through CTGAN and graph-based deep learning

引用

NETWORK MODELING AND ANALYSIS IN HEALTH INFORMATICS AND BIOINFORMATICS 2024年第1期13卷 48页

作者： Naik, Anushka Patwardhan, Ishan Joshi, Amit COEP Technol Univ COEP Tech Dept Comp Sci & Engn Wellesley Rd Pune 411005 Maharashtra India

This research proposes a novel method for enhancing the prediction of microbe-disease associations and the identification of possible drug treatments through the utilization of advanced computational strategies. The foundation of this approach is the integration of data from the Human Microbe-Disease Association Database with advanced techniques such as Conditional Tabular Generative Adversarial Networks for augmenting data and a combination of Graph Neural Networks and Graph Attention Networks for modeling the intricate relationships between microbes and diseases. Additionally, this study leverages the bidirectional encoder representations from transformers for the encoding of diseases and drugs, thereby improving the prediction capabilities for disease-drug associations. A thorough experimental analysis validates the efficacy of these approaches in decoding complex biological datasets, offering valuable insights into disease etiology and potential treatment pathways. The results highlight the significance of merging generative models, graph-based deep learning, and transformer-based natural language processing models to push forward the boundaries of biomedical research and its applications.

关键词： Graph neural networks Graph attention networks Disease-drug associations Generative adversarial network bidirectional encoder representations from transformers

来源：评论

学校读者我要写书评

暂无评论

Aspect term extraction and optimized deep learning for sentiment classification

引用

SOCIAL NETWORK ANALYSIS AND MINING 2024年第1期14卷 221页

作者： Adilakshmi, Konda Srinivas, Malladi Anuradha, K. Srilakshmi, V. Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram Andhra Prades India Gokaraju Rangaraju Inst Engn & Technol GRIET Dept CSE Hyderabad 500090 India

Sentiment or opinion largely relies on public commentary, where reflections are either positive or negative. Sentiment classification automates the process of determining the orientation of a subject based on text, which aims to classify documents by expressed views. This task faces significant challenges due to issues, like negation, ambiguity, and complex language structures. In this work, a new Squirrel Search Mayfly Algorithm_Hierarchical Deep Learning for Text (SSMA_HDLTex) is established for sentiment classification using aspect term extraction and optimized deep learning. Primarily, the document on Amazon review is taken as input and later it is applied to the process of tokenization. In this process, bidirectional encoder representations from transformers is employed to partition the sentence into tokens. Later, Aspect Term Extraction is effectuated. At last, sentiment classification is done by employing HDLTex which is trained by utilizing the presented SSMA method. The novel SSMA method is devised by integrating the Squirrel Search Algorithm as well as the Mayfly Algorithm. The proposed SSMA_HDLTex has attained maximal and precision, F-measure, and recall, of 0.936, 0.937, and 0.941correspondingly. This innovative approach significantly enhances the accuracy and reliability of sentiment classification tasks.

关键词： Squirrel search algorithm Mayfly optimization algorithm bidirectional encoder representations from transformers Squirrel search Mayfly algorithm Hierarchical deep learning for text

来源：评论

学校读者我要写书评

暂无评论

Political Hate Speech Detection and Lexicon Building: A Study in Taiwan

引用

IEEE ACCESS 2022年 10卷 44337-44346页

作者： Wang, Chih-Chien Day, Min-Yuh Wu, Chun-Lian Natl Taipei Univ Grad Inst Informat Management New Taipei 23741 Taiwan

There is the minimal restriction to users' speech in cyberspace. The Internet provides a space where people can freely present their speech, which puts a Utopian sense of freedom of speech into practice. However, the appearance of hate speech is a significant side effect of online freedom of speech. Some users use hate speech to attack others, making the attacked targets uncomfortable. The proliferation of hate speech poses severe challenges to cyber society. Users may hope that social media platforms and online communities promote anti-hate speech. However, hate speech detection is still a developing technology that requires system developers to create a method to detect unacceptable hate speech while maintaining the online freedom of speech environment. No excellence detection approach has yet been proposed, although some literature has focused on it. The current study proposes an approach to build a political hate speech lexicon and train artificial intelligence classifiers to detect hate speech. Our academic and practical contributions include the collection of a Chinese hate speech dataset, creating a Chinese hate speech lexicon, and developing both a deep learning-based and a lexicon-based approach to detect Chinese hate speech. Although we focus on Chinese hate speech detection, our proposed hate speech detection system and hate speech lexicon development approach can also be used for other languages.

关键词： Hate speech Social networking (online) Blogs Support vector machines Feature extraction Logistics Convolutional neural networks BERT bidirectional encoder representations from transformers deep learning hate speech lexicon N-gram natural language processing TF-IDF

来源：评论

学校读者我要写书评

暂无评论

GBRE-AHB: contextual understanding for cross-domain aspect categorization with adaptive hyperparameter tuning

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第SUPPL 1期18卷 43-55页

作者： Kumaragurubaran, T. Chiranjeevi, V. Rahul Elangovan, D. Kumar, S. Vinodh Rajalakshmi Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India Panimalar Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India

The cross-domain aspect detection and categorization is a vital task in natural language processing, enabling the automated identification and categorization of aspects in textual data spanning diverse domains. Traditional methods face several complexities such as scalability, limited contextual understanding of words, data sparsity, and adaptation difficulty. So, a novel method named gated bidirectional recurrent encoder-based adaptive honey badger (GBRE-AHB) algorithm is proposed for cross-domain aspect detection and categorization. In this study, the bidirectional encoder representations for transformers (BERT) is utilized to capture contextual information from text and enable better aspect identification and categorization by understanding the context. The local optimization problems are identified and solved by determining an adaptive strategy. Also, the gated recurrent unit (GRU) is employed to sequence the text data and allow aspect detection by considering the sequence in which aspects appear within a document. The study is validated on the datasets, namely the IMDB dataset of 50 K movie reviews and the cell phone reviews sentiment analysis-body dataset. The efficiency is validated by various metrics that attained the ranges as F1-score (97.85%), specificity (97.83%), recall (97.82%), precision (97.94%), and accuracy (98.67%), respectively. The experimental results revealed that the proposed method for cross-domain aspect detection and categorization as well as improved the reliability as well as longevity of the model and determined the impacts applied in the categorization process.

关键词： Cross-domain aspect detection bidirectional encoder representations from transformers Gated recurrent unit Honey badger optimization Adaptive strategy Stemming Tokenization Lemmatization Stop word removal

来源：评论

学校读者我要写书评

暂无评论

A Cross-Attention BERT-Based Framework for Continuous Sign Language Recognition

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 1818-1822页

作者： Zhou, Zhenxing Tam, Vincent W. L. Lam, Edmund Y. Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China

Continuous sign language recognition (CSLR) is a challenging task involving various signal processing techniques to infer the sequences of glosses performed by signers. Existing approaches in CSLR typically use multiple input modalities such as the raw video data and the extracted hand images to improve their recognition accuracy. However, the large modality differences make it difficult to define an integrative framework to effectively exchange and combine the knowledge obtained from different modalities such that they can complement each other for improving the framework's robustness against the gesture variations and background noises in CSLR. To address this issue, we propose a novel cross-attention deep learning framework named the CA-SignBERT. This framework utilizes multiple bidirectional encoder representations from transformers (BERT) models to analyze the information from different modalities. Among these BERT models, we introduce a special cross-attention mechanism to ensure an efficient inter-modality knowledge exchange. Besides, an innovative weight control module is proposed to dynamically hybridize their outputs. Experimental results reveal that the CA-SignBERT framework attains state-of-the-art performance in four benchmark CSLR datasets.

关键词： Feature extraction Bit error rate Weight control Data mining Assistive technologies Training Gesture recognition Attention mechanism sign language recognition bidirectional encoder representations from transformers

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：