检索结果-内蒙古大学图书馆

15th international conference on Learning Analytics and knowledge

作者： Li, Ziqing Cukurova, Mutlu Bulathwela, Sahan UCL Dept Comp Sci London England UCL UCL Knowledge Lab London England UCL Ctr Artificial Intelligence London England

ISBN: (纸本)9798400707018

The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses fine-tuning on a pre-trained T5-small model, employing specially created datasets tailored to educational needs. The research further explores the impacts of pre-training strategies, quantisation, and data augmentation on the model's performance. We specifically address the challenge of generating semantically aligned questions with paragraph-level contexts, thereby improving the topic specificity of the generated questions. In addition, we introduce and explore novel evaluation methods to assess the topical relatedness of the generated questions. Our results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions. These models have the potential to reduce teacher workload and support personalised tutoring systems by serving as bespoke question generators. With its relatively small number of parameters, the proposals not only advance the capabilities of question generation models for handling specific educational topics but also offer a scalable solution that reduces infrastructure costs. This scalability makes them feasible for widespread use in education without reliance on proprietary large language models like ChatGPT.

关键词： Educational Question Generation Formative Assessment Summative Assessment Personalised Testing natural language processing

来源：评论

学校读者我要写书评

暂无评论

Fake news detection using natural language processing

Fake news detection using natural language processing

引用

2025 international conference on Computer, Electrical and Communication engineering, ICCECE 2025

作者： Varma, M. Jaswanth Rohit, M. Sai Selvi, G. Sabeena Gnana Sathyabhama institute of science and technology Department of Cse Chennai India

ISBN: (纸本)9798331513894

Fake news is rampart in the society of the current country and has caused the society to distrust the media, fake news is chosen over real news articles. As a result in the current paper, we discuss the application of natural language processing methods in the identification of fake news on the different platforms. Here we present an unobtrusive framework to automatically interpret news articles as real or fake based on supervised learning with the help of feature extraction from natural language processing. This method contains features based on textual elements which include syntactic features, semantic features and features that speaks about the sentiment of the given content in detail. We enhance feature representation by incorporating pre-trained word embeddings and transformer-based models such as BERT which relieves the amount of structural design and hence, results in better classification accuracy. The experiments we want to propose rely on a dataset containing a set of different news sources;to provide a more realistic scenario, when tuning the model, we use a balanced combination of real news and fake ones, using made up stories. To assess the effectiveness of the proposed framework, we employ tools for performance assessment, namely: precision, recall and F1 score to detect fake information. This result also shows the importance of context and shows how NLP techniques can distinguish between two forms of language use that typically define fake news. In addition, we explain how our work relates to prior research on media literacy and the creation of algorithms for journalists and non-journalists alike. Moreover, our research contributes to the stream of studies that aim at applying NLP for enhancing the effectiveness of combating fake news and the emergence of the society that is better equipped to function within the information logistics of the digital world. All in all, the present overall study focuses on whether advanced language processing tools rem

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Federated Prototype Guided Adaption for Vision-language Models

Federated Prototype Guided Adaption for Vision-Language Mode...

引用

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

作者： Liu, Youchao Huang, Dingjiang School of Data Science and Engineering East China Normal University Shanghai China

ISBN: (纸本)9798350368741

Federated Learning (FL) is a new pivotal paradigm for decentralized training on heterogeneous data. Recently fine-tuning of Vision-language Models (VLMs) has been extended to the federated setting to improve overall performance. Unfortunately, in this case, FL still faces two critical challenges that hinder its actual performance: data distribution heterogeneity and high resource costs brought by large VLMs. In this paper, we introduce FedPGA, a prototype-guided method, for achieving performance improvements in the federated setting for VLMs. Concretely, we design a prototype-based adapter for the vision-language model, CLIP. The lightweight adapter updates the prior knowledge encoded in CLIP to enhance its adaption capability further and avoid the effects of data distribution heterogeneity in the federated setting. Simultaneously, small-scale operations can mitigate the computational and communication burden caused by large VLMs. Our comprehensive empirical evaluations of nine diverse image classification datasets show that our method is superior to existing FL methods under VLMs. © 2025 IEEE.

关键词： federated learning few-shot classification prototype-based adapter vision-language model

来源：评论

学校读者我要写书评

暂无评论

Utilizing Deep Learning and natural language processing to Elucidate Neural Activity in Human Listeners 6

Utilizing Deep Learning and Natural Language Processing to E...

引用

6th international conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Algani, Yousef Methkal Abd Saravanakumar, R. Department of Mathematics The Arab Academic College of Education in Israel Haifa Israel Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (纸本)9798331522667

Identifying the neural substrates of human auditory system has been a classic pursuit that fell into the list of grand challenges in neuroscience. Deep learning and natural language processing towards the end of the last decade have given a fruitful way to decipher and interpret neurons concerned with audio perception. This paper describes how these technologies may be used to enhance understanding of neural activity in human listeners. This will begin by defining the general auditory perception and the neural architecture supporting it before proceeding to review the insights learned from applying deep learning and natural language processing to demystify neural signals. Activity that occurs in the human brain is very important in the development of neuroscience, cognitive science and artificial intelligence. Here the effort has been made to try to figure out how CNN, RNN, and NLP could be integrated for the purpose of building a model to study the neural responses evoked by auditory stimuli. Selecting CNNs for feature extraction and RNNs for modeling of the temporal sequence consequently applying advanced elaboration of natural language processing we are aimed to reveal the intricate neural patterns for language and sound processing. As a training and testing dataset we have used Human Connectome Project with 1200 neural images total. It attained a 91.2% accuracy while applying in the Python platform using Keras and tensorflow. Implications and relevance: The results of this work may have significance for further neuroscientific research, the creation of the systems of brain-computer interfaces, and thinking about the problems connected with privacy and consent. The paper demonstrates how deep learning and the NLP application alter the ways in which we look at auditory processing by the brain and future work in neuroscience and more. © 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

PROMPTIST: Automated Prompt Optimization for Text-to-Image Synthesis 13th

PROMPTIST: Automated Prompt Optimization for Text-to-Image S...

引用

13th international conference on natural language processing and Chinese Computing

作者： Li, WeiJie Wane, Jin Zhang, Xuejie Yunnan Univ Kunming Yunnan Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Recent advancements in text-to-image synthesis (TIS) models, such as DALL-E 3 and stable diffusion XL, have significantly improved image quality. However, these models typically require experts with artistic and photographic expertise to create model-preferred prompts for high-quality image generation, a requirement that challenges non-experts in real-world applications. This study proposes PROMPTIST, an automated framework that optimizes user-original prompts into model-preferred prompts, thereby enabling TIS models to produce more aesthetically pleasing images. We employ the retrieval augmented generation (RAG) technique with Large language Models (LLMs) to automatically refine prompts, ensuring that the proposed framework is broadly applicable and extends beyond the specific models' styles like stable diffusion or DALL-E. Furthermore, to ensure the LLMs generate visually appealing images, we fine-tuned a quality assessment model to analyze prompt quality and provide necessary feedback to the LLMs. The proposed prompt engineering method for LLMs can significantly enhance the quality of both prompts and images. Extensive experimental results consistently demonstrate PROMPTIST's superiority over strong baselines.

关键词： Retrieve Augmented Generation Large language Models Text-to-image

来源：评论

学校读者我要写书评

暂无评论

China-aided conference buildings in developing countries: a mosaic analysis of database

引用

JOURNAL OF ASIAN ARCHITECTURE AND BUILDING engineering 2025年第3期24卷 1027-1044页

作者： Ma, Kaiyue Xue, Charlie Chang, Wei Univ Chinese Acad Sci Ctr Architectural Res & Design Zhongguancun East Rd Beijing 100190 Peoples R China City Univ Hong Kong Coll Engn Dept Architectural & Civil Engn Hong Kong Peoples R China Tangshan Normal Univ Sch Fine Arts Tangshan Hebei Peoples R China Yanshan Univ Sch Civil Engn & Mech Yanshan Hebei Peoples R China

The China-aided conference building has garnered global attention due to its diplomatic implications, symbolic representation, iconic stature, and bilateral cultural expression. These constructions play a significant role in the cross-cultural communication of Chinese architecture under the One Belt and One Road Initiative (BRI). Despite the prevalence of such buildings with China's aid, there exists a substantial gap in the systematic and comprehensive research on this topic. This study constructed a database of 157 China-aided conference buildings, spanning from 1962 to 2022. This data was subsequently analyzed by a mosaic approach, employing a model of six indicators across two dimensions: macro characteristics and building ontology. The results indicate that the macro-distribution characteristics mirror China's trends in international cooperation and development and are closely tied to China's political policies and economic conditions. Chinese architects exhibit eclectic expressions, incorporating modern architectural language, local culture, and Chinese architectural culture. These findings also highlight the ongoing evolution of the Chinese architectural knowledge system. This research complements Chinese architecture and China's aid, offering designers, researchers, and policymakers in cross-border architecture a comprehensive perspective and design trends of China-aided conference buildings. This is particularly beneficial for the cross-cultural communication of overseas architectural cooperation under the BRI.

关键词： China-aided conference buildings time-space distribution cross-cultural expression developing countries the BRI

来源：评论

学校读者我要写书评

暂无评论

Establishing Traceability Between natural language Requirements and Software Artifacts by Combining RAG and LLMs 43rd

Establishing Traceability Between Natural Language Requireme...

引用

43rd international conference on Conceptual Modeling

作者： Ali, Syed Juried Naganathan, Varun Bork, Dominik TU Wien Business Informat Grp Vienna Austria Microsoft Hyderabad India

ISBN: (纸本)9783031758713;9783031758720

Software engineering aims to effectively translate stakeholders' requirements into executable code to fulfill their needs. Traceability from natural language use case requirements to classes in a UML class diagram, subsequently translated into code implementation, is essential in systems development and maintenance. Tasks such as assessing the impact of changes and enhancing software reusability require a clear link between these requirements and their software implementation. However, establishing such links manually across extensive codebases is prohibitively challenging. Requirements, typically articulated in natural language, embody semantics that clarify the purpose of the codebase. Conventional traceability methods, relying on textual similarities between requirements and code, often suffer from low precision due to the semantic gap between high-level natural language requirements and the syntactic nature of code. The advent of Large language Models (LLMs) provides new methods to address this challenge through their advanced capability to interpret both natural language and code syntax. Furthermore, representing code as a knowledge graph facilitates the use of graph structural information to enhance traceability links. This paper introduces an LLM-supported retrieval augmented generation approach for enhancing requirements traceability to the class diagram of the code, incorporating keyword, vector, and graph indexing techniques, and their integrated application. We present a comparative analysis against conventional methods and among different indexing strategies and parameterizations on the performance. Our results demonstrate how this methodology significantly improves the efficiency and accuracy of establishing traceability links in software development processes.

关键词： Large language Models LLM Requirements Traceability Retrieval Augmented Generation Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Do Large language Models Mirror Cognitive language processing? 31

Do Large Language Models Mirror Cognitive Language Processin...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： Ren, Yuqi Jin, Renren Zhang, Tongxuan Xiong, Deyi College of Intelligence and Computing Tianjin University China College of Computer and Information Engineering Tianjin Normal University China

ISBN: (纸本)9798891761964

Large language Models (LLMs) have demonstrated remarkable abilities in text comprehension and logical reasoning, indicating that the text representations learned by LLMs can facilitate their language processing capabilities. In neuroscience, brain cognitive processing signals are typically utilized to study human language processing. Therefore, it is natural to ask how well the text embeddings from LLMs align with the brain cognitive processing signals, and how training strategies affect the LLM-brain alignment? In this paper, we employ Representational Similarity Analysis (RSA) to measure the alignment between 23 mainstream LLMs and fMRI signals of the brain to evaluate how effectively LLMs simulate cognitive language processing. We empirically investigate the impact of various factors (e.g., pre-training data size, model scaling, alignment training, and prompts) on such LLM-brain alignment. Experimental results indicate that pre-training data size and model scaling are positively correlated with LLM-brain similarity, and alignment training can significantly improve LLM-brain similarity. Explicit prompts contribute to the consistency of LLMs with brain cognitive language processing, while nonsensical noisy prompts may attenuate such alignment. Additionally, the performance of a wide range of LLM evaluations (e.g., MMLU, Chatbot Arena) is highly correlated with the LLM-brain similarity. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AutOnto: Towards A Semi-Automated Ontology engineering Methodology 6th

AutOnto: Towards A Semi-Automated Ontology Engineering Metho...

引用

6th international conference on knowledge Graphs and Semantic Web, KGSWC 2024

作者： Arevalo, Kiara Marnitt Ascencion Ambre, Shruti Dorsch, Rene Technische Hochschule Georg Simon Ohm Nuremberg Germany Fraunhofer Institute for Integrated Circuits IIS Nuremberg Germany

ISBN: (纸本)9783031812200

This paper addresses the challenge of efficiently constructing domain ontologies for large, rapidly evolving domains, where manual approaches often struggle to overcome knowledge acquisition bottlenecks. To overcome these limitations, we developed an automated framework, AutOnto, for knowledge extraction and ontology conceptualization that leverages Large language Models (LLMs) and natural language processing (NLP) techniques. AutOnto integrates BERT-based topic modeling with LLMs to automate the extraction of concepts and relationships from text corpora, facilitating the construction of taxonomies and the generation of domain ontologies. We applied AutOnto to a dataset of NLP-specific articles from OpenAlex and compared the resulting ontology generated by our automated process against a well-established gold-standard ontology. The results indicate that AutOnto achieves comparable levels of quality and correctness while significantly reducing the amount of data required and the dependence on domain-specific expertise. These findings highlight AutOnto’s efficiency and effectiveness in knowledge extraction and ontology generation. This work has significant implications for rapid ontology development in large, evolving domains, potentially mitigating the knowledge acquisition bottleneck in ontology engineering. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Causal Relationship Detection Using Prompt engineering and Large language Models 9

Enhancing Causal Relationship Detection Using Prompt Enginee...

引用

Joint Workshop of the 9th Financial Technology and natural language processing, FinNLP 2025, the 6th Financial Narrative processing, FNP 2025, and the 1st Workshop on Large language Models for Finance and Legal, LLMFinLegal 2025, co-located with the 31st international conference on Computational Linguistics, COLING 2025

作者： Chatwal, Pulkit Agarwal, Amit Mittal, Ankush Rajiv Gandhi Institute of Petroleum Technology Jais India AICoE Wells Fargo International Solutions Private Limited Bangalore India COER University Roorkee India

ISBN: (纸本)9798891762091

Causal relationships are essential for understanding financial systems, offering insights into market dynamics, regulatory impacts, and organizational decisions. Traditional approaches to detecting causality in financial texts often struggle with the nuanced and domain-specific language of such disclosures. The FinCausal 2025 shared task provided a benchmark for evaluating advanced methods in multilingual financial causality detection. In this work, we employ prompt engineering with large language models (LLMs) to identify causal relationships in financial disclosures across languages. Our system achieved Semantic Answer Similarity (SAS) scores of 0.9086 in English and 0.8987 in Spanish, with Exact Match (EM) scores of 0.5110 and 0.0619, respectively. These results demonstrate the potential of LLMs for tackling the challenges of causality detection in multilingual and domain-specific contexts, while also identifying areas for future refinement. © 2025 Association for Computational Linguistics.

关键词： Decentralized finance

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：