检索结果-内蒙古大学图书馆

Enhancing stock price prediction using GANs and transformer-based attention mechanisms

empirical ECONOMICS 2025年第1期68卷 373-403页

作者： Li, Siyi Xu, Sijie Univ Coll Dublin Quinn Business Sch Dublin Ireland ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China

Stock price prediction plays an important role in financial decision-making, enabling investors and analysts to make informed choices regarding trading and investment strategies. Traditional statistical methods have been utilized for the prediction of stock price, but it is often difficult for them to capture complex patterns, adapt to changing market conditions, handle large datasets, and automatically extract relevant features. Recent advancements in machine learning and deep learning offer promising solutions to address these challenges. In this paper, we propose a new approach to enhance the stock price prediction by leveraging generative adversarial networks (GANs) and transformer-based attention mechanisms. GANs are utilized to generate synthetic stock price data, and incorporating market sentiment and volatility. Attention mechanisms will selectively concentrate on the important features and patterns in the data, which may do good to the identification of key market indicators which will impact stock prices. By integrating market social media news which can tell about the sentiment and volatility, our model aims to improve the accuracy and robustness of stock price forecasts. We also address the limitations of GANs and attention mechanisms separately used in stock price prediction, such as unrealistic data generation and overfitting, by employing regularization techniques and incorporating additional data sources. Experimental evaluations using real-world stock market data will be conducted to compare the performance of our proposed models with conventional approaches. The findings of this research have implications for investors, financial analysts, and other stakeholders who are engaged in the stock market ecosystem, providing valuable insights for the investment strategies.

关键词： Deep learning Stock prediction GANs natural language processing

来源：评论

学校读者我要写书评

暂无评论

Application of natural language processing Algorithms for Chatbots 17

Application of Natural Language Processing Algorithms for Ch...

引用

17th IEEE International conference on Computer Research and Development, ICCRD 2025

作者： Smajic, Azra Music, Denis Džeemal Bijedić University of Mostar Faculty of Information Technologies Bosnia and Herzegovina

ISBN: (纸本)9798331531881

In recent years, there has been a significant increase in published research on deploying various machine learning (ML) methods and algorithms in the development of chatbots for diverse applications. Substantial evidence indicates that top IT companies globally employ intelligent solutions to improve customer service and support. Typical chatbot implementation often involves rule-based systems, where each question is matched with a specific rule or predefined response. However, this principle is impractical for vast amounts of data, where users can always ask questions that are out of the scope of predefined rules. This paper demonstrates the implementation of NLP algorithms in chatbots, using machine learning and custom Python functions to improve user interaction by accurately answering domain-specific questions and providing appropriate feedback for questions outside its scope. © 2025 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders

MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoder...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Wenyu Zhang Shuo Sun Bin Wang Xunlong Zou Zhuohan Liu Yingxu He Geyu Lin Nancy F. Chen Ai Ti Aw Institute for Infocomm Research (I2R) Agency for Science Technology and Research (A*STAR) Singapore Centre for Frontier AI Research (CFAR) Agency for Science Technology and Research (A*STAR) Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-trained audio encoder has constrained capacity to capture features for new tasks and datasets. To address this, we propose to incorporate mixtures of ‘weak’ encoders (MoWE) into the AudioLLM framework. MoWE supplements a base encoder with a pool of relatively lightweight encoders, selectively activated based on the audio input to enhance feature extraction without significantly increasing model size. Our empirical results demonstrate that MoWE effectively improves multi-task performance, broadening the applicability of AudioLLMs to more diverse audio tasks.

关键词： Large language models Speech enhancement Signal processing Multitasking Feature extraction natural language processing Acoustics

来源：评论

学校读者我要写书评

暂无评论

MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training 25

MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-...

引用

30th International conference on Architectural Support for Programming languages and Operating Systems-ASPLOS

作者： Cai, Weilin Qin, Le Huang, Jiayi Hong Kong Univ Sci & Technol Guangzhou Guangzhou Peoples R China

ISBN: (纸本)9798400710797

As large language models continue to scale up, distributed training systems have expanded beyond 10k nodes, intensifying the importance of fault tolerance. Checkpoint has emerged as the predominant fault tolerance strategy, with extensive studies dedicated to optimizing its efficiency. However, the advent of the sparse Mixture-of-Experts (MoE) model presents new challenges due to the substantial increase in model size, despite comparable computational demands to dense models. In this work, we propose the Mixture-of-Checkpoint System (MoC-System) to orchestrate the vast array of checkpoint shards produced in distributed training systems. MoC-System features a novel Partial Experts Checkpointing (PEC) mechanism, an algorithm-system co-design that strategically saves a selected subset of experts, effectively reducing the MoE checkpoint size to levels comparable with dense models. Incorporating hybrid parallel strategies, MoC-System involves fully sharded checkpointing strategies to evenly distribute the workload across distributed ranks. Furthermore, MoC-System introduces a two-level checkpointing management method that asynchronously handles in-memory snapshots and persistence processes. We build MoC-System upon the Megatron-DeepSpeed framework, achieving up to a 98.9% reduction in overhead for each checkpointing process compared to the original method, during MoE model training with ZeRO-2 data parallelism and expert parallelism. Additionally, extensive empirical analyses substantiate that our methods enhance efficiency while maintaining comparable model accuracy, even achieving an average accuracy increase of 1.08% on downstream tasks.

关键词： Fault Tolerance Checkpoint Mixture of Experts Large language Models Training

来源：评论

学校读者我要写书评

暂无评论

GraphVCM: Virtual Center Mixing with Distance-Aware Regulation for Class Imbalanced Node Classification

GraphVCM: Virtual Center Mixing with Distance-Aware Regulati...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Ren, Yixiao Han, Yunfei Wang, Yi Luo, Zhengdong Liu, Jinlong Ma, Yupeng Xinjiang Technical Institute of Physics & Chemistry Chinese Academy of Sciences Urumqi China University of Chinese Academy of Sciences Beijing China Xinjiang Laboratory of Minority Speech and Language Information Processing Urumqi China

ISBN: (纸本)9798350368741

Class imbalance is a prevalent issue in real-world graph-structure data, such as social and citation networks, posing significant challenges for Graph Neural Networks (GNNs). Existing solutions often focus on balancing class distributions via oversampling techniques, which may lead to overfitting and blurred decision boundaries between majority and minority classes. To address this issue, we propose GraphVCM, a novel virtual center mixing with distance-aware regulation approach for class imbalanced node classification. GraphVCM first leverages spectral clustering to generate virtual center nodes, representing the features of majority class samples. These virtual centers are then mixed with minority class nodes to synthesize new nodes for enhancing minority class representation. Moreover, we introduce a distance-aware regulation module to optimize the inter-class decision boundaries by simultaneously maximizing inter-class distances and minimizing intra-class distances. Extensive experiments on multiple public datasets demonstrate that GraphVCM consistently outperforms state-of-the-art methods and effectively alleviates the negative impact of class imbalance. © 2025 IEEE.

关键词： class imbalance data augmentation node classification virtual centroid features

来源：评论

学校读者我要写书评

暂无评论

Trends in Bio-Based 3D Concrete Printing: An NLP-Driven Analysis 4th

Trends in Bio-Based 3D Concrete Printing: An NLP-Driven Anal...

引用

4th International conference on Sustainable Development in Civil, Urban and Transportation Engineering, CUTE 2024

作者： Rajczakowska, Magdalena Department of Civil Environmental and Natural Resources Engineering Luleå University of Technology Luleå97187 Sweden

ISBN: (纸本)9789819793990

The EU Bioeconomy Strategy underscores the importance of fostering a shared understanding of the shift to a bioeconomy and raising awareness of the diverse biomass demand. Since concrete is a globally prevalent material with a substantial environmental impact, it presents an enticing opportunity to integrate biomass products. Particularly, in the context of the burgeoning interest in digital concrete manufacturing, the use of bio-based cementitious "ink" could offer a promising resolution to the environmental challenges faced by the construction sector. This paper examines the current trends in substituting traditional concrete components with bio-based materials, such as bio-binders and bio-admixtures, for use in 3D printing technologies. natural language processing (NLP) methods are employed to extract features from a substantial number of published documents automatically. This process aids in identifying the most frequently occurring bio-based ingredients and their biomass sources. Latent Dirichlet Allocation (LDA) is utilized to perform topic modeling and unveil underlying patterns within the corpus. A comprehensive discussion of both current and potential future developments is conducted. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bioeconomy

来源：评论

学校读者我要写书评

暂无评论

Application and Development of natural language processing Algorithm System in Corpus Linguistics

Application and Development of Natural Language Processing A...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International conference on

作者： Yingying Wei Department of Human Resources Wanjiang University of Technology Maanshan China

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

In the digital age, the explosive growth of information has led to significant challenges such as the burden of reading long texts, cross-language communication barriers, and information overload. To address these issues, this paper investigates the application and development of natural language processing (NLP) algorithm systems in corpus linguistics. We employ two methods for automatic summary generation-extractive and generative-which identify key sentences or phrases and utilize Seq2Seq models to produce natural and fluent summaries. For machine translation, we build a multi-language parallel corpus and train a neural machine translation (NMT) model using statistical techniques and the Transformer architecture with attention mechanisms. This approach enhances translation accuracy and fluency. Additionally, we explore summarization technology to combat information overload, improving summary relevance and accuracy through multi-task learning and generative adversarial networks (GANs). Our Re3Sum model further guides text summary generation using real summaries as soft templates. That the Transformer-based model significantly outperforms traditional methods in accuracy, fluency, and information retention, achieving a maximum information retention score of 88.76 points. This reduces the burden of reading long texts and enhances cross-language communication efficiency. Overall, this study not only offers new research directions for the NLP field but also provides practical solutions to language processing challenges.

关键词： Integrated circuits Accuracy Translation Neural machine translation Linguistics Transformers Multitasking Information age Generative adversarial networks natural language processing

来源：评论

学校读者我要写书评

暂无评论

Citation Based Scientific Document Summarization Using Deep Learning 4th

Citation Based Scientific Document Summarization Using Deep ...

引用

4th International conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Jyoti, Divya Srivastava, Jyoti Mahato, Dharmendra Prasad Natl Inst Technol Hamirpur Dept Comp Sci & Engn Hamirpur 177005 Himachal Prades India

ISBN: (纸本)9783031837920;9783031837937

With the rapid increase in the volume of scientific literature, researchers face challenges in keeping up with the latest advancements while summarizing the documents. Scientific document text summarization offers a solution by providing concise and informative summaries that highlight the key contributions from original texts. This study introduces a novel method leveraging deep learning, specifically the sBERT model to summarize scientific documents. The proposed approach treats the extractive summarization as a classification problem using a dual BERT model setup. The methodology is evaluated using data set from CL-SciSumm. Results indicate that our approach significantly outperforms the existing methods in terms of ROUGE scores, demonstrating its effectiveness in generating accurate summaries of scientific literature.

关键词： Citation Based Summarization Scientific Documentation Deep Learning BERT and sBERT model natural language processing

来源：评论

学校读者我要写书评

暂无评论

Utilizing Large language Models for Developing Automatic Question Generation in Education

Utilizing Large Language Models for Developing Automatic Que...

引用

2025 International conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Winata, Ardiansyah Jaya Surjawan, Daniel Jahja Mawardi, Viny Christanti Tarumanagara University Faculty of Informatics Engineering Jakarta Indonesia Maranatha Christian University Faculty of Smart Engineering and Technology Bandung Indonesia

ISBN: (纸本)9798331513320

The increasing workload of educators, particularly in manual question creation, poses a significant challenge in modern education. Manual question creation demands time, effort, and a deep understanding of the material to ensure contextual and curriculum-aligned questions. To address this, an Automatic Question Generation (AQG) system was developed using extractive summarization combined with the PEGASUS and TextRank methods. The system leverages natural language processing (NLP) and transformer-based large language models (LLMs) to efficiently generate relevant questions. The primary data source for this system was digital social studies (IPS) books from the Indonesian Ministry of Education. The evaluation was conducted using ROUGE Score metrics and human assessments. ROUGE analysis yielded an average F1 score of 0.87 (ROUGE-1), 0.83 (ROUGE-2), and 0.84 (ROUGE-L), demonstrating the system's effectiveness in capturing essential information. Human evaluations involving educators and students highlighted the relevance and contextual accuracy of generated questions, particularly for structured materials. The system generated questions within 2 to 6 minutes, showcasing its efficiency in reducing educators' workload. However, challenges remain in handling materials with implicit semantic relationships or nonlinear narratives, as PEGASUS struggles to maintain contextual relevance. This limitation may lead to irrelevant questions and answers, indicating a need for improved semantic understanding. This study concludes that the PEGASUS+TextRank AQG system is a promising tool to streamline question generation. Future improvements in semantic algorithms and broader training data are crucial to enhancing the system's reliability and adaptability to diverse educational contexts. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical Trial Documents 31

RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical ...

引用

31st International conference on Computational Linguistics, COLING 2025

作者： Ji, Changkai Zhao, Bowen Wang, Zhuoyao Wang, Yingwen Zhang, Yuejie Cheng, Ying Feng, Rui Zhang, Xiaobo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China National Children's Medical Center Children's Hospital of Fudan University Shanghai China

ISBN: (纸本)9798891761964

Randomized Controlled Trials (RCTs) are rigorous clinical studies crucial for reliable decision-making, but their credibility can be compromised by bias. The Cochrane Risk of Bias tool (RoB 2) assesses this risk, yet manual assessments are time-consuming and labor-intensive. Previous approaches have employed Large language Models (LLMs) to automate this process. However, they typically focus on manually crafted prompts and a restricted set of simple questions, limiting their accuracy and generalizability. Inspired by the human bias assessment process, we propose RoBGuard, a novel framework for enhancing LLMs to assess the risk of bias in RCTs. Specifically, RoBGuard integrates medical knowledge-enhanced question reformulation, multimodal document parsing, and multi-expert collaboration to ensure both completeness and accuracy. Additionally, to address the lack of suitable datasets, we introduce two new datasets: RoB-Item and RoB-Domain. Experimental results demonstrate RoBGuard's effectiveness on the RoB-Item dataset, outperforming existing methods. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

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：