检索结果-内蒙古大学图书馆

13th International Conference on computing and Pattern Recognition, ICCPR 2024

作者： Liu, Haijing Seman, Noraini Department of Computer Engineering Taiyuan Institute of Technology Shanxi Taiyuan China College of Computing Informatics and Mathematics University Technology MARA Shah Alam Selangor Malaysia

ISBN: (纸本)9798400717482

In the field of multilingual machine translation, many pretrained language models have achieved the inspiring results. However, the results based on pretrained models are not yet very satisfactory for low-resource languages. This paper investigates how to leverage code-switching data to fine-tune pretrained multilingual machine translation model, in order to boost the performance of few-shot low resource machine translation. By utilizing a multilingual mixed corpus, the code-switching method can enhance the cross-linguistic generalization ability of the model and improve its overall understanding of the language. In this paper, on the smaller size model of FLORES-101 benchmark, we use the code-switching data augmentation method to achieve the results of benchmark's larger model on six direction pairs of three languages, Chinese, English and Malay. This paper studied various corpus mixture mechanisms to construct the data in code-switching, and the experimental findings show that the results using the code-switching fine-tuning model improve the spBLEU score by an average of 2 to 3 points over the results without code-switching. © 2024 Copyright held by the owner/author(s).

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Mobile Learning Technologies as drivers of School Enrolment Levels in South Africa: A Policy Simulation Experiment using Machine Learning-Driven Dynamic Autoregressive Distributed Lag Model 24

Mobile Learning Technologies as drivers of School Enrolment ...

引用

Proceedings of the 37th International BCS Human-Computer Interaction Conference

作者： Fatima Ahmad Muazu Festus Adedoyin Huseyin Dogan Paul Whittington Nicholas Mavengere Dept. of Computing & Informatics Bournemouth University UK

This study addresses the imperative challenge of enhancing school enrolment in South Africa by investigating the dynamics of mobile learning technologies, internet access, and key socio-economic variables. Spanning 35 years (1998–2022), the research draws from the National Digital and Future Skills Strategy, aiming to provide insights into the factors influencing educational access. Employing an analytical framework that integrates Autoregressive Distributed Lag (ARDL), dynamic ARDL (dynARDL) simulations, and Kernel-based Regularized Least Squares (KRLS) machine learning, the study finds that economic prosperity, as represented by real GDP per capita, positively influences secondary school enrolment. Mobile phone subscribers emerge as a significant driver, emphasizing the transformative potential of digital technologies. Surprisingly, an inverse relationship between internet users and enrolment prompts a reassessment of the role of internet access in education. The dynARDL simulations introduce counterfactual shocks, highlighting the positive impact of a 10% increase in mobile subscribers and the nuanced consequences of changes in internet users. KRLS analysis reinforces the significance of economic indicators, digital technologies, and human development in shaping enrolment. Drawing policy implications, the study advocates targeted investments in digital infrastructure, strategic approaches to internet access optimization, and policies fostering sustainable economic growth.

关键词： Mobile Learning

来源：评论

学校读者我要写书评

暂无评论

DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models

arXiv

引用

arXiv 2025年

作者： Bae, Suyoung Choi, YunSeok Lee, Jee-Hyong College of Computing and Informatics Sungkyunkwan University Korea Republic of

While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot methods are efficient but fail to consider context and prevent bias propagation in the answers. To address this, we propose DeCAP, a method for debiasing LLMs using Context-Adaptive Prompt Generation. DeCAP leverages a Question Ambiguity Detection to take appropriate debiasing actions based on the context and a Neutral Answer Guidance Generation to suppress the LLMs make objective judgments about the context, minimizing the propagation of bias from their internal knowledge. Our various experiments across eight LLMs show that DeCAP achieves state-of-the-art zero-shot debiased QA performance. This demonstrates DeCAP’s efficacy in enhancing the fairness and accuracy of LLMs in diverse QA settings. Our code is publicly available at https://***/BaeSuyoung/DeCAP. © 2025, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Stunting Classification Among Toddlers Using Decision Tree C4.5 in Berastagi City

Stunting Classification Among Toddlers Using Decision Tree C...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Hygea Saveria Putu Harry Gunawan Informatics School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Stunting is a condition where a child's height significantly falls below the average for their age, primarily due to prolonged malnutrition and inadequate nutrient intake. This condition poses long-term challenges, affecting both physical growth and cognitive development. This study focuses on developing a predictive model using the C4.5 Decision Tree algorithm to classify the stunting status of children under five. The dataset comprises nutritional status data of toddlers collected from the Berastagi Health Center. Incorporating attributes such as gender, birth weight and height, age in months, weight, height, and the height-to-age ratio. The model aims to enhance the accuracy of stunting classification to support targeted prevention and treatment strategies. When compared to Naive Bayes, the Decision Tree C4.5 demonstrated superior performance, achieving an F1 score and average accuracy of 86%. This reflects a robust balance between precision and recall, underscoring its reliability in identifying children at risk of stunting. The research highlights the critical role of data-driven methodologies in public health. With its high accuracy, the model serves as a promising tool for healthcare providers, enabling more effective interventions to reduce stunting prevalence and improve nutritional outcomes among children under five years of age.

关键词： Pediatrics Accuracy Prevention and mitigation Urban areas Vegetation Predictive models Prediction algorithms Decision trees Reliability Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs 31

Empirical Study on Data Attributes Insufficiency of Evaluati...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Chuang Jin, Renren Yao, Zheng Li, Tianyi Cheng, Liang Steedman, Mark Xiong, Deyi College of Intelligence and Computing Tianjin University China School of Electrical Engineering and Computer Science University of Queensland Australia School of Informatics University of Edinburgh United Kingdom

ISBN: (纸本)9798891761964

Previous benchmarks for evaluating large language models (LLMs) have primarily emphasized quantitative metrics, such as data volume. However, this focus may neglect key qualitative data attributes that can significantly impact the final rankings of LLMs, resulting in unreliable leaderboards. In this paper, we investigate whether current LLM benchmarks adequately consider these data attributes. We specifically examine three attributes: diversity, redundancy, and difficulty. To explore these attributes, we propose a framework with three separate modules, each designed to assess one of the attributes. Using a method that progressively incorporates these attributes, we analyze their influence on the benchmark. Our experimental results reveal a meaningful correlation between LLM rankings on the revised benchmark and the original benchmark when these attributes are accounted for. These findings indicate that existing benchmarks often fail to meet all three criteria, highlighting a lack of consideration for multifaceted data attributes in current evaluation datasets. © 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

Optimizing Prompt Engineering for Automated Text Summarization of Student Reflections: A Comparative Study Using GPT-4 LLM 2025

Optimizing Prompt Engineering for Automated Text Summarizati...

引用

Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 2

作者： Nicole Wiktor Computing and Informatics UNC Charlotte Charlotte NC USA

ISBN: (纸本)9798400705328

In the educational domain, extracting insights from student-written text has shown to be valuable for instructors. Efficiently summarizing students' reflections in a course offers instructors valuable insights to enhance students' learning experience. Therefore, quickly understanding students' impressions about the course could be very helpful to instructors for in-time and/or personalized one-on-one discussions. Achieving this often involves using natural language processing (NLP) techniques Understanding capabilities of LLMs through a series of comparative experiments involving prompt engineering is the goal of this work. We compare the summarization outputs of GPT-4 with an experimentally optimized temperature of 0.75 through a variety of experiments that include different levels of prompts, starting with base level and proceeding to increase context in the prompt. We evaluate and compare the outputs of these summaries based on a rubric from literature, evaluated by human annotators. Our findings suggest that providing more detailed context prompts help LLMs uncover less frequent and obvious student challenges and provide more detailed explanations. One notable finding showed how sensitive the LLM approach is to the distribution of the challenge types in students' reflections. In other words, all prompts regardless of their contextual details faced issues due to this misrepresenting of student challenges distributions, sometimes overstating their occurrence frequency. Therefore, further study is required to refine the data distribution impact. Despite this, the approach shows much potential to extract useful knowledge quickly. It offers valuable insights to instructors and could help in supporting students more effectively.

关键词： GPT-4

来源：评论

学校读者我要写书评

暂无评论

Cross-validation for training and testing co-occurrence network inference algorithms

引用

BMC Bioinformatics 2025年第1期26卷 1-24页

作者： Agyapong, Daniel Propster, Jeffrey Ryan Marks, Jane Hocking, Toby Dylan School of Informatics Computing and Cyber Systems Northern Arizona University FlagstaffAZ United States Department of Biological Sciences Northern Arizona University FlagstaffAZ United States Département d’informatique Université de Sherbrooke Sherbrooke Canada

Background : Microorganisms are found in almost every environment, including soil, water, air and inside other organisms, such as animals and plants. While some microorganisms cause diseases, most of them help in biological processes such as decomposition, fermentation and nutrient cycling. Much research has been conducted on the study of microbial communities in various environments and how their interactions and relationships can provide insight into various diseases. Co-occurrence network inference algorithms help us understand the complex associations of micro-organisms, especially bacteria. Existing network inference algorithms employ techniques such as correlation, regularized linear regression, and conditional dependence, which have different hyper-parameters that determine the sparsity of the network. These complex microbial communities form intricate ecological networks that are fundamental to ecosystem functioning and host health. Understanding these networks is crucial for developing targeted interventions in both environmental and clinical settings. The emergence of high-throughput sequencing technologies has generated unprecedented amounts of microbiome data, necessitating robust computational methods for network inference and validation. Results : Previous methods for evaluating the quality of the inferred network include using external data, and network consistency across sub-samples, both of which have several drawbacks that limit their applicability in real microbiome composition data sets. We propose a novel cross-validation method to evaluate co-occurrence network inference algorithms, and new methods for applying existing algorithms to predict on test data. Our method demonstrates superior performance in handling compositional data and addressing the challenges of high dimensionality and sparsity inherent in real microbiome datasets. The proposed framework also provides robust estimates of network stability. Conclusions : Our empirical study show

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pricing Models in E-Commerce: Exploring Machine Learning Techniques to Balance Profitability and Customer Satisfaction

引用

IEEE Access 2025年 13卷 72994-73002页

作者： Guo, Xiaochen Zhang, Lei Management School of Anhui Business and Technology College Hefei230041 China Anhui Business and Technology College School of Information Engineering Hefei230041 China University of Technology MARA College of Computing Informatics and Mathematics Selangor Shah Alam40450 Malaysia

This research investigates the application of Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) networks, paired with gradient-based optimization techniques for dynamic pricing in e-commerce. The primary objective is to develop a pricing model that effectively balances profitability with customer satisfaction by leveraging sequential data, such as time-series and customer behavior patterns. The approach utilizes LSTM’s ability to capture long-term dependencies in sequential data, while optimization methods like Stochastic Gradient Descent (SGD) enhance model convergence and performance. Key findings include the superior predictive accuracy of LSTM-based models over traditional approaches like Linear Regression and Decision Trees, particularly in real-time data updates and price elasticity scenarios. Additionally, the analysis revealed that LSTM models could efficiently adapt pricing strategies in response to market dynamics, significantly improving profitability while maintaining customer satisfaction. This study provides valuable insights into the application of advanced machine learning techniques in e-commerce pricing. The results suggest that LSTM-based dynamic pricing models could optimize revenue generation, offering substantial implications for pricing strategy development in modern retail environments. Future work may explore hybrid models and multi-objective optimization techniques to further refine these models. © 2013 IEEE.

关键词： User experience

来源：评论

学校读者我要写书评

暂无评论

SmartDeco: AR for Soft Furnishing Design 1st

SmartDeco: AR for Soft Furnishing Design

引用

1st International Conference on Extended Reality, ICXR 2024

作者： Wang, Jingyuan Zhang, Yichun Liu, Ruilong Chen, Shiyi Hu, Yang Yao, Junfeng Beijing University of Posts and Telecommunications Haidian District Beijing China Center for Digital Media Computing School of Film School of Informatics Xiamen University Xiamen361005 China

ISBN: (纸本)9789819636785

Augmented reality (AR) is increasingly being integrated into the home renovation sector, yet current AR solutions often fail to address the challenges of soft decoration design. This study introduces SmartDeco, an AR-based application for the Chinese market, enhanced by large language models (LLMs) to improve user experiences in home decoration. Serving merchants, interior designers, and users, SmartDeco enables AR simulations of soft furnishing combinations, supports collaborative design, and utilizes LLMs to offer real-time design recommendations, addressing potential issues and improving decision-making. User testing demonstrates SmartDeco’s effectiveness in enhancing usability, simplifying design processes, reducing errors, and boosting satisfaction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Knowledge augmented significant language model-based chatbot for explainable diabetes mellitus prediction 19

Knowledge augmented significant language model-based chatbot...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Elfayoumi, Mazen AbouElazm, Mohamed Mohamed, Omar Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt Faculty of Computer Science Goldsmith UOL United Kingdom College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

This study proposes an innovative diabetes prediction chatbot that utilizes large language models (LLMs) to determine the likelihood of diabetes based on specific patient inputs. Unlike conventional machine learning models and in addition to providing precise, individualized, robust prediction of diabetes augmented by the percentage of its confidence, this chatbot provides detailed text-based explanations for its individual predictions and enhances user’s understanding by retrieving and presenting similar cases using case-based reasoning techniques. Utilizing key health indicators such as hypertension status, heart disease presence, smoking history, BMI, HbA1c level, and blood glucose levels, the chatbot not only predicts the presence of diabetes but also educates users about the underlying reasons for each prediction. The system's explanation module promotes transparency and trust in the predictive process. The proposed architecture integrates the retrieval augmented generation (RAG) technique with prompt engineering across multiple LLMs, including Llama 3.1, GPT-3.5, and Gemma2. This approach augments the chatbot’s responses with contextually relevant data from similar past cases, thereby enhancing both relevance and accuracy. Furthermore, RAG minimizes LLM hallucinations while enhancing them with up-to-date, precise, personalized medical information. The objective of this chatbot is to offer healthcare professionals and patients a dependable, educational instrument for early detection of diabetes supported by transparent AI principles. This will have a positive effect on preventative healthcare measures. © 2025 IEEE.

关键词： Prediction models

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：