检索结果-内蒙古大学图书馆

4th International Conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Jin, Jiayong Dong, Yongquan He, Bugui Zhou, Nan Yan, Linke School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou221116 China Xuzhou Cloud Computing Engineering Technology Research Center Jiangsu Xuzhou221116 China Jiangsu Engineering Technology Research Center of ICT in Education Jiangsu Xuzhou221116 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Existing MOOC review sentiment classification methods do not fully utilize the local context information associated with aspect, and they ignore the connection between local and global contexts, while resulting in modeled features that lack the information connection between aspect and contexts. In this paper, we propose a model that incorporates Local Context Focus (LCF) and Bi-Directional Gated Recurrent Unit (Bi-GRU). First, the BERT model is used to dynamically encode course reviews. Then, global semantic features are extracted using the Bi-GRU model to strengthen the connection between the preceding and following texts. Then, the LCF model based on multi-head self-attention is used to obtain local contextual features and splice them with global semantic features. Finally, the Softmax function is utilized to output the classification results. The experimental accuracies of the proposed model on the three MOOC course review datasets reach 97.96%, 96.76%, and 94.16%, respectively, which are improved by 0.70%, 0.42%, and 0.03% over the suboptimal baseline model. The proposed model significantly improves the effectiveness of MOOC course review sentiment classification, and provides a useful reference for the optimization and improvement of MOOC courses. © 2025 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Instance-adaptive Zero-shot Chain-of-Thought Prompting

arXiv

引用

arXiv 2024年

作者： Yuan, Xiaosong Shen, Chen Yan, Shaotian Zhang, Xiaofeng Xie, Liang Wang, Wenxiao Guan, Renchu Wang, Ying Ye, Jieping College of Computer Science and Technology Jilin University China Alibaba Cloud Computing China Shanghai Jiao Tong University China College of Software Zhejiang University China

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in realworld reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA- 3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8K, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Collusion Resistant Identity-based Proxy Re-encryption Scheme on Lattice 6

Collusion Resistant Identity-based Proxy Re-encryption Schem...

引用

6th International Conference on Computer Information science and Application technology, CISAT 2023

作者： Deng, Xiaohong Xie, Hua Xiong, Weizhi School of Electronics and Information Engineering Gannan University of Science and Technology Ganzhou341000 China College of Information Science Jiangxi University of Science and Technology Ganzhou341000 China Key Laboratory of Cloud Computing and Big Data Ganzhou341000 China

ISBN: (纸本)9781510668546

Proxy re-encryption plays an important role for data security in cloud computing and big data, but the traditional reencryption scheme based on the classical number theory problem cannot resist quantum attack, and the lattice based cryptosystem has been proved to have the ability to resist quantum attack, so the lattice based re-encryption scheme has always been a research hotspot. In view of the problem that collusion-resistance and multi-hop can not be satisfied at the same time in existing schemes, this paper proposes a new identity-based proxy re-encryption scheme on lattice. Firstly, the scheme uses trapdoors as private keys to achieve one-way anti-collusion. In addition, we constructs a variant of learning with errors (LWE), which uses a convert algorithm to transform the user matrix and replace the vector with a uniform matrix, so that the scheme can meet the requirements of multi-hop and encrypt multiple bits of messages at one time. Theoretical analysis and experimental simulation prove that the security of the new scheme can be reduced to a decision LWE problem, which can reach the IND-sID-CPA security in the standard model, and can improve the encryption efficiency while ensuring the security. © 2023 SPIE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs

arXiv

引用

arXiv 2024年

作者： Chen, Liyi Tong, Panrong Jin, Zhongming Sun, Ying Ye, Jieping Xiong, Hui University of Science and Technology China Alibaba Cloud Computing China Thrust of Artificial Intelligence The Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Large Language Models (LLMs) have shown remarkable reasoning capabilities on complex tasks, but they still suffer from out-of-date knowledge, hallucinations, and opaque decision-making. In contrast, Knowledge Graphs (KGs) can provide explicit and editable knowledge for LLMs to alleviate these issues. Existing paradigm of KG-augmented LLM manually predefines the breadth of exploration space and requires flawless navigation in KGs. However, this paradigm cannot adaptively explore reasoning paths in KGs based on the question semantics and self-correct erroneous reasoning paths, resulting in a bottleneck in efficiency and effect. To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer. Specifically, three important mechanisms of Guidance, Memory, and Reflection are designed to work together, to guarantee the adaptive breadth of self-correcting planning for graph reasoning. Finally, extensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of PoG. © 2024, CC BY-NC-ND.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Web Service Recommendation Based on Knowledge Graph Enhanced

Web Service Recommendation Based on Knowledge Graph Enhanced

引用

2023 International Conference on cloud computing, Performance computing, and Deep Learning, CCPCDL 2023

作者： Huang, Xinyi Zhao, Gansen School of Computer Science South China Normal University Guang Zhou China Guangzhou Key Lab on Cloud Computing Security and Assessment Technology Guang Zhou China

ISBN: (纸本)9781510666474

Mashup is an information system development project based on Web services. It can build new business processes by mixing data, resources and APIs from different sites or applications, and meet new user needs. However, in recent years, the number of Web API is increasing quickly, and it is difficult for developers and users to find suitable Mashups, which influences the development and functional efficiency of information systems. Therefore, designing an accurate and efficient Web service recommendation method to improve the functional characteristics of information systems has become a research hotspot. At present, many algorithms, like matrix factorization and collaborative filtering, often have serious cold start and sparse problems. In order to alleviate the above problems and capture as much information as possible, we proposed a multi-modal knowledge graph enhancement recommendation method (MKE), which combines structured information and unstructured information of Mashup and Web API. Firstly, the feature information is mined from the text description of API and Mashup to assist the construction of the service recommendation system. Then, the knowledge graph is constructed by using the related attributes and relationships of Mashup and API, as well as the entity and relationship of Mashup and API, and the text features. The low-dimensional embedded Trans model provides Top-K recommendation results for the specified Mashup description. Finally, experiments are carried out on the latest ProgrammableWeb dataset, and the experimental results show that the recommendation performance of this method is better than that of RippleNet, NCF, CKE, KGCN. © 2023 SPIE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering 62

How Proficient Are Large Language Models in Formal Languages...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Liu, Jinxin Cao, Shulin Shi, Jiaxin Zhang, Tingjian Nie, Lunyiu Hu, Linmei Hou, Lei Li, Juanzi Department of Computer Science and Technology BNRist China THU - Siemens Ltd. China Joint Research Center for Industrial Intelligence and IoT Tsinghua University Beijing China Huawei Cloud Computing Technologies Co. Ltd. China School of Computer Science and Technology Beijing Institute of Technology China

ISBN: (纸本)9798891760998

Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance. However, although it is validated that LLMs are capable of solving some KBQA problems, there has been little discussion on the differences in LLMs' proficiency in formal languages used in semantic parsing. In this work, we propose to evaluate the understanding and generation ability of LLMs to deal with differently structured logical forms by examining the inter-conversion of natural and formal language through in-context learning of LLMs. Extensive experiments with models of different sizes show that state-of-the-art LLMs can understand formal languages as well as humans, but generating correct logical forms given a few examples remains a challenge. Most importantly, our results also indicate that LLMs exhibit considerable sensitivity. In general, the formal language with a lower formalization level, i.e., the more similar it is to natural language, is more friendly to LLMs. Code and data can be found at https://***/Matthewlliu/structure_probe. © 2024 Association for Computational Linguistics.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Research on cloud Health Privacy Information Protection Algorithm Based on Data Mining 3rd

Research on Cloud Health Privacy Information Protection Algo...

引用

3rd EAI International Conference on IoT and Big Data Technologies for Health Care, IotCARE 2022

作者： Wang, Wennan Song, Shiyang Zhu, Linkai Su, Junyu Guo, Te Tang, Jinhai Academy of Management Guangdong University of Science and Technology Dongguan523083 China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai519099 China Information Technology School Hebei University of Economics and Business Shijiazhuang050061 China Institute of Data Science City University of Macau 999078 China

ISBN: (纸本)9783031335440

In the process of selecting privacy evaluation indicators, the original algorithm did not set the degree of protection risk, which resulted in a little error in the protection of privacy information, which affected the efficiency of data operation. A data mining-based cloud health privacy information protection algorithm was studied. Build a differential privacy information protection model, establish the connection relationship between users and information, and use trapezoidal distribution membership function to determine the sensitive attributes of privacy information. Set up health privacy information protection indicators on the cloud, evaluate the risks of privacy information protection, and classify them into three levels: high, medium and low. Based on data mining, the information privacy mode is extracted, and the minimum support threshold is used to judge the support of private information in the database. Set the privacy information protection algorithm in the way of data support estimation. Experimental results: in the given data set, the support error of the algorithm in this paper is within 1.5%, and the error of the traditional algorithm is more than 5%. With the increasing size of the data set, the execution time of the traditional algorithm is much higher than that of the algorithm in this paper, which shows that the design is effective. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

STRUCTURE-ENHANCED PROTEIN INSTRUCTION TUNING: TOWARDS GENERAL-PURPOSE PROTEIN UNDERSTANDING

arXiv

引用

arXiv 2024年

作者： Wu, Wei Wang, Chao Chen, Liyi Yin, Mingze Zhu, Yiheng Fu, Kun Ye, Jieping Xiong, Hui Wang, Zheng School of Artificial Intelligence and Data Science University of Science and Technology of China China College of Computer Science and Technology Zhejiang University China Alibaba Cloud Computing China China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Proteins, as essential biomolecules, play a central role in biological processes, including metabolic reactions and DNA replication. Accurate prediction of their properties and functions is crucial in biological applications. Recent development of protein language models (pLMs) with supervised fine tuning provides a promising solution to this problem. However, the fine-tuned model is tailored for particular downstream prediction task, and achieving general-purpose protein understanding remains a challenge. In this paper, we introduce Structure-Enhanced Protein Instruction Tuning (SEPIT) framework to bridge this gap. Our approach integrates a noval structure-aware module into pLMs to inform them with structural knowledge, and then connects these enhanced pLMs to large language models (LLMs) to generate understanding of proteins. In this framework, we propose a novel twostage instruction tuning pipeline that first establishes a basic understanding of proteins through caption-based instructions and then refines this understanding using a mixture of experts (MoEs) to learn more complex properties and functional information with the same amount of activated parameters. Moreover, we construct the largest and most comprehensive protein instruction dataset to date, which allows us to train and evaluate the general-purpose protein understanding model. Extensive experimental results on open-ended generation and closed-set answer tasks demonstrate the superior performance of SEPIT over both closed-source general LLMs and open-source LLMs trained with protein knowledge. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization

引用

IEEE Transactions on Visualization and Computer Graphics 2023年第1期29卷 331-341页

作者： Ying, Lu Shu, Xinhuan Deng, Dazhen Yang, Yuchen Tang, Tan Yu, Lingyun Wu, Yingcai Zhejiang University State Key Lab of CAD&CG Hangzhou China Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Hong Kong School of Art and Archaeology Zhejiang University Hangzhou China Xi'an Jiaotong-Liverpool University Department of Computing Suzhou China

Glyph-based visualization achieves an impressive graphic design when associated with comprehensive visual metaphors, which help audiences effectively grasp the conveyed information through revealing data semantics. However, creating such metaphoric glyph-based visualization (MGV) is not an easy task, as it requires not only a deep understanding of data but also professional design skills. This paper proposes MetaGlyph, an automatic system for generating MGVs from a spreadsheet. To develop MetaGlyph, we first conduct a qualitative analysis to understand the design of current MGVs from the perspectives of metaphor embodiment and glyph design. Based on the results, we introduce a novel framework for generating MGVs by metaphoric image selection and an MGV construction. Specifically, MetaGlyph automatically selects metaphors with corresponding images from online resources based on the input data semantics. We then integrate a Monte Carlo tree search algorithm that explores the design of an MGV by associating visual elements with data dimensions given the data importance, semantic relevance, and glyph non-overlap. The system also provides editing feedback that allows users to customize the MGVs according to their design preferences. We demonstrate the use of MetaGlyph through a set of examples, one usage scenario, and validate its effectiveness through a series of expert interviews. © 2022 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Treasures in Discarded Weights for LLM Quantization 39

Treasures in Discarded Weights for LLM Quantization

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Hao Zhou, Yang Chen, Bohua Yang, Zelan Li, Shen Li, Yong Wu, Jianxin National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Alibaba Cloud Computing China

ISBN: (纸本)157735897X

In recent years, large language models (LLMs) have developed rapidly and revolutionized natural language processing. However, high storage overhead and computing costs limit LLM deployment in resource-constrained environments. Quantization algorithms can effectively compress LLMs and accelerate inference, but they lead to loss in precision, especially in low-bit scenarios. In this paper, we find that the discarded weight values caused by quantization in fact contain treasures to improve LLMs’ accuracy. To excavate those hidden treasures, we construct search spaces around these discarded weights and those weights within the search space can seamlessly be incorporated into the original quantization weights. To determine which weights should be merged, we design a plug-and-play weight compensation framework to capture global information and keep the weights with the highest potential benefits. Our framework can be combined with various LLM quantization algorithms to achieve higher precision without additional inference overhead. We validate the effectiveness of our approach on widely used benchmark datasets for LLMs. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Natural language processing systems

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：