检索结果-内蒙古大学图书馆

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Mutsaddi, Atharva Choudhary, Aditya Department of Computer Science and Engineering COEP Technological University India

ISBN: (纸本)9798891762152

Plagiarism involves using another persons work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi - one of India’s regional languages - it is crucial to design robust plagiarism detection systems tailored for low-resource languages. Language models like Bidirectional Encoder Representations from Transformers (BERT) have demonstrated exceptional capability in text representation and feature extraction, making them essential tools for semantic analysis and plagiarism detection. However, the application of BERT for low-resource languages remains under-explored, particularly in the context of plagiarism detection. This paper presents a method to enhance the accuracy of plagiarism detection for Marathi texts using BERT sentence embeddings in conjunction with Term Frequency-Inverse Document Frequency (TF-IDF) feature representation. This approach effectively captures statistical, semantic, and syntactic aspects of text features through a weighted voting ensemble of machine learning models. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Methods for Sentiment Analysis in Climate Change Conversations: A Comparative Review 1

Transformer-Based Methods for Sentiment Analysis in Climate ...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Dayama, Shreya J Deshmukh, Pratiksha R COEP Technological University Department of Computer Engineering Pune India

ISBN: (纸本)9798350355611

Climate change poses a critical global threat, influencing the environment, economy, and human well-being. Key drivers like increasing greenhouse gas emissions, deforestation, and industrial activities are contributing to substantial environmental shifts. Public sentiment about climate change plays a pivotal role in shaping policies and advocating for actions to mitigate its impacts. Incorporating sensor data into sentiment analysis introduces a fresh approach to capturing real-time environmental conditions, providing an additional layer of insight to complement traditional text-based sentiment analysis. This research aims to address existing gaps by comparing the effectiveness of various transformer models for detecting climate change sentiment. Although sentiment analysis has predominantly relied on textual data, there is a noticeable gap in exploring the potential of sensor data in this area. Previous studies have focused primarily on analyzing social media posts, news reports, and other written sources, often overlooking the valuable perspective that sensor data can provide. This study seeks to bridge this gap by integrating environmental sensor data to enhance the accuracy and contextual relevance of climate change sentiment analysis [15]. The main goal is to evaluate the capabilities of different transformer models in analyzing climate change sentiment. This research will assess each model's strengths and limitations, determine the most effective one for specific elements of sentiment analysis, and offer recommendations to guide future research in this field. By increasing the variety of data sources and the overall precision of climate sentiment detection, the results seek to improve sentiment analysis approaches. © 2025 IEEE.

关键词： Greenhouse gas emissions

来源：评论

学校读者我要写书评

暂无评论

BERTopic for Topic Modeling of Hindi Short Texts: A Comparative Study 1

BERTopic for Topic Modeling of Hindi Short Texts: A Comparat...

引用

1st Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages, IndoNLP 2025

作者： Mutsaddi, Atharva Jamkhande, Anvi Thakre, Aryan Haribhakta, Yashodhara Department of Computer Science and Engineering COEP Technological University India

ISBN: (纸本)9798891762145

As short text data in native languages like Hindi increasingly appear in modern media, robust methods for topic modeling on such data have gained importance. This study investigates the performance of BERTopic in modeling Hindi short texts, an area that has been under-explored in existing research. Using contextual embeddings, BERTopic can capture semantic relationships in data, making it potentially more effective than traditional models, especially for short and diverse texts. We evaluate BERTopic using 6 different document embedding models and compare its performance against 8 established topic modeling techniques, such as Latent Dirichlet Allocation (LDA), Non-negative Matrix Factorization (NMF), Latent Semantic Indexing (LSI), Additive Regularization of Topic Models (ARTM), Probabilistic Latent Semantic Analysis (PLSA), Embedded Topic Model (ETM), Combined Topic Model (CTM), and Top2Vec. The models are assessed using coherence scores across a range of topic counts. Our results reveal that BERTopic consistently outperforms other models in capturing coherent topics from short Hindi texts. © 2025 Association for Computational Linguistics.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Transforming Sentimental Analysis: Applying Deep Learning with BERT and GPT for X Data Insights

Transforming Sentimental Analysis: Applying Deep Learning wi...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Varma, Manthan S Ghosh, Soma Coep Technological University Computer Science & Engineering Pune India

ISBN: (纸本)9798331521394

Social media platforms like X have become key channels for expressing opinions and sentiments, creating vast amounts of textual data. Analyzing this data to understand public sentiment is crucial for various applications, including market research, political analysis, and customer feedback. Traditional sentiment analysis methods often struggle with the nuances of language, especially in informal settings like X. However, recent advancements in deep learning, particularly with transformer models such as BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pre-trained Transformer), have significantly improved the accuracy of sentiment analysis. These models use attention mechanisms to capture the context of words within a sentence, allowing for a more sophisticated understanding of sentiment. Unlike existing studies that predominantly focus on either BERT or GPT separately, this research provides a comparative evaluation of their effectiveness for sentiment analysis on X, highlighting their strengths and limitations in handling informal and context-dependent text. BERT, with its bidirectional approach, and GPT, known for its text generation capabilities, have achieved state-of-the-art results in numerous NLP tasks. This study leverages these models to analyze the Sentiment140 dataset, aiming to enhance sentiment analysis on X by utilizing deep learning techniques and libraries like Hugging Face Transformers, PyTorch, and TensorFlow. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Sunflower Disease Detection: CNN Feature Extraction and ML Model Evaluation 3

Hybrid Approach for Sunflower Disease Detection: CNN Feature...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： More, Mrunal Deshmukh, Pratiksha Tanksale, Rushikesh Coep Technological University Department Of Computer Engineering Pune India Two Registers Pune India

ISBN: (纸本)9798331509675

Sunflower diseases like Alternaria blight, downy mildew, and rust are a major menace to agricultural output and require effective and precise detection mechanisms. Labor-consuming and human error-prone conventional manual inspection methods make automated machine learning-based detection more useful than ever before. This research paper introduces a deep learning technique based on the fusion of CNN-based feature extraction with machine learning-based classifiers for classifying sunflower diseases. A new dataset of 466 sunflower leaf images, such as Downy Mildew, Fresh Leaves, Gray Mold, and Leaf Scars, was created to support this study. Different machine learning algorithms, such as Support Vector Machines (SVM), Naïve Bayes (NB), Random Forest (RF), and K-Nearest Neighbors (KNN), were compared using CNN-extracted features. The model proposed, using transfer learning with ResNet-50 and sophisticated augmentation strategies, had a 90% overall accuracy rate, surpassing conventional classifiers and a baseline CNN model. Experimental results show that the model is resilient in the presence of real-world issues like class imbalance, data heterogeneity, and annotation noise. The research provides a robust and efficient framework for diagnosing sunflower disease, which can be used in precision agriculture and automated plant health monitoring. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning

引用

Chinese Journal of Electronics 2025年第1期34卷 98-113页

作者： Hengmin Zhang Jian Yang Wenli Du Bob Zhang Zhiyuan Zha Bihan Wen School of Electrical and Electronic Engineering Nanyang Technological University School of Computer Science and Engineering Nanjing University of Science and Technology School of Information Science and Engineering East China University of Science and Technology Department of Electrical and Computer Engineering University of Macau

Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.

关键词： Learning systems Image recognition Minimization Computational efficiency Complexity theory Matrix decomposition Optimization Image reconstruction Singular value decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

LegalAI Across Languages: A Comprehensive Survey on Tasks, Methodologies and Challenges 1

LegalAI Across Languages: A Comprehensive Survey on Tasks, M...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Deshpande, Anjali Deshmukh, Pratiksha COEP Technological University Dept. of Computer Science and Engineering Pune India PICT Dept. of AI & DS Pune India School of Computational Sciences COEP Technological University Dept. of Computer Science and Engineering Pune India

ISBN: (纸本)9798350355611

Natural Language Processing (NLP) is revolutionizing the legal domain, enabling tasks such as predicting legal outcomes, summarizing complex documents, identifying key entities, and assessing bail risks. This survey paper presents a comprehensive review of the existing research on NLP tasks applied to legal documents and judgments across various languages, with a special emphasis on low-resource languages. Despite the extensive work done in widely spoken languages like English, there remains a critical need to extend these advancements to languages with limited resources and data availability. This paper categorizes and analyzes the NLP tasks in the legal domain based on the languages they target. It highlights the methodologies employed, datasets utilized, and the performance of different models across diverse languages. Furthermore, it identifies the gaps in current research and proposes potential directions for future work, particularly in improving the accessibility and applicability of NLP solutions for legal texts in underrepresented languages. By providing a comprehensive overview of advancements and obstacles, this survey seeks to assist future research endeavors that bridge the disparity between high-resource and low-resource languages in legalAI applications. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

ProtGAT: Refining Antimicrobial Resistance Detection with Graph-Based Deep Learning∗ 1

ProtGAT: Refining Antimicrobial Resistance Detection with Gr...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Naik, Anushka Naik, Akanksha Deshmukh, Pratiksha COEP Technological University Department of Computer Science and Engineering Pune India Ruby Hall Clinic Pune Pune India

ISBN: (纸本)9798350355611

The rise of antimicrobial resistance (AMR) is a critical threat to global health, necessitating urgent advancements in diagnostic capabilities. Current methods for detecting AMR are hampered by slow processing times and a lack of precision, making early and accurate detection challenging. This paper introduces ProtGAT, a novel computational framework that combines ProteinBERT and Graph Attention Networks (GAT) to enhance the detection of AMR. Our model leverages deep learning to analyze complex protein sequences and their interactions, improving the accuracy of AMR predictions. The integration of ProteinBERT provides a robust feature extraction from protein sequences, while GAT focuses on identifying key relational features within these sequences. Early testing of ProtGAT demonstrates its superior performance over traditional models, particularly in identifying novel AMR sequences that evade conventional detection methods. This study highlights the potential of advanced computational approaches to revolutionize AMR diagnostics, offering faster and more reliable tools for healthcare providers in combating this growing public health concern. © 2025 IEEE.

关键词： Antimicrobial Resistance Computational Biology Graph Attention Networks Protein Sequence Analysis ProteinBERT

来源：评论

学校读者我要写书评

暂无评论

WSO-KELM: War Strategy Optimization-Based Kernel Extreme Learning Machine for Automatic Software Fault Prediction Model

引用

Journal of The Institution of Engineers (India): Series B 2025年第1期106卷 145-163页

作者： Elci, J. Brundha Nandagopalan, S. Department of Computer Science and Engineering Vemana Institute of Technology Visvesvaraya Technological University Karnataka Belagavi India Department of Information Science and Engineering Vemana Institute of Technology Visvesvaraya Technological University Karnataka Belagavi India

The software development projects’ testing part is usually expensive and complex, but it is essential to gauge the effectiveness of the developed software. Software Fault Prediction (SFP) primarily serves to detect faults within software components. The scale of software projects is getting larger, making it impossible and time-consuming to analyze the flaws manually. Artificial Intelligence (AI) techniques are mainly incorporated to solve this problem. The massive data retrieved from the software repositories helps in identifying the features that are highly correlated with fault prediction and the features that are not. This paper introduces a Kernel Extreme Learning Machine (KELM) for SFP. To optimize the hyperparameters of the classifier and also enhance the classification accuracy, the War Strategy Optimization (WSO) algorithm is employed here. The experimental evaluations are conducted using different baseline actual-world datasets of software programs such as Java-coded open-source and PROMISE datasets. The experimental outcomes are conducted using different performance metrics that include sensitivity, Accuracy, and F1-score with values of 0.96%, 0.97%, and 0.96%, respectively. The results show that KELM is beneficial, and the optimization provided by the WSO algorithm also helps us obtain higher classification accuracy for the SFP problem and improve the fault detection process. © The Institution of Engineers (India) 2024.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

Multi-channel mantis search spatial attention convolutional neural network based hyperspectral image change detection

引用

Multimedia Tools and Applications 2025年 1-22页

作者： Divya, V.M. Department of Computer Science and Engineering East West Institute of Technology Visvesvaraya Technological University Belagavi560018 India

Hyperspectral imaging has transformed remote sensing by offering detailed spectral data for monitoring environmental changes, like urban development and terrestrial cover variations. However, existing change detection techniques often face challenges like underfitting and overfitting. In this research, a novel approach is introduced for hyperspectral image change detection using a Multi-Channel Mantis Search (MCMS). This innovative methodology leverages the power of a Multi-Channel Convolutional Neural Network (MCNN) to process each spectral band independently, facilitating the capture of unique features within each band. The input hyperspectral images are gathered from the Pavia university Dataset and the Indian Pines Dataset. This approach leads to significantly improved feature extraction, enhancing the discrimination of different materials in hyperspectral images. To further enhance the performance of the change detection model, the Mantis Search Algorithm (MSA) is integrated. The MSA is employed to optimize the model's hyperparameters, fine-tuning its architecture and training parameters to achieve superior results. The combination of MCNN and MSA improves hyperspectral image change detection accuracy, achieving 98.21% and 99.31% with the Indian Pines and Pavia university datasets correspondingly. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

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：