检索结果-内蒙古大学图书馆

Large language model for table processing: a survey

Frontiers of Computer Science 2025年第2期19卷 71-87页

作者： Weizheng LU Jing ZHANG Ju FAN Zihao FU Yueguo CHEN Xiaoyong DU School of Information Renmin University of ChinaBeijing 100872China Key Laboratory of Data Engineering and Knowledge Engineering Beijing 100872China WPS Office Kingsoft Co.Zhuhai 519080China

Tables,typically two-dimensional and structured to store large amounts of data,are essential in daily activities like database queries,spreadsheet manipulations,Web table question answering,and image table information *** these table-centric tasks with Large Language Models(LLMs)or Visual Language Models(VLMs)offers significant public benefits,garnering interest from academia and *** survey provides a comprehensive overview of table-related tasks,examining both user scenarios and technical *** covers traditional tasks like table question answering as well as emerging fields such as spreadsheet manipulation and table data *** summarize the training techniques for LLMs and VLMs tailored for table ***,we discuss prompt engineering,particularly the use of LLM-powered agents,for various tablerelated ***,we highlight several challenges,including diverse user input when serving and slow thinking using chainof-thought.

关键词： data mining and knowledge discovery table processing large language model

来源：评论

学校读者我要写书评

暂无评论

Enhancing Storage Efficiency and Performance: A Survey of data Partitioning Techniques

引用

Journal of Computer Science & Technology 2024年第2期39卷 346-368页

作者：刘鹏举李翠平陈红 Distinguished Member CCF 1.School of InformationRenmin University of ChinaBeijing 100872China Key Laboratory of Data Engineering and Knowledge Engineering of the Ministry of Education Beijing 100872China

data partitioning techniques are pivotal for optimal data placement across storage devices,thereby enhancing resource utilization and overall system ***,the design of effective partition schemes faces multiple challenges,including considerations of the cluster environment,storage device characteristics,optimization objectives,and the balance between partition quality and computational ***,dynamic environments necessitate robust partition detection *** paper presents a comprehensive survey structured around partition deployment environments,outlining the distinguishing features and applicability of various partitioning strategies while delving into how these challenges are *** discuss partitioning features pertaining to database schema,table data,workload,and runtime *** then delve into the partition generation process,segmenting it into initialization and optimization stages.A comparative analysis of partition generation and update algorithms is provided,emphasizing their suitability for different scenarios and optimization ***,we illustrate the applications of partitioning in prevalent database products and suggest potential future research directions and *** survey aims to foster the implementation,deployment,and updating of high-quality partitions for specific system scenarios.

关键词： data partitioning survey partitioning feature partition generation partition update

来源：评论

学校读者我要写书评

暂无评论

Study on the Characteristics of Cross-Domain knowledge Diffusion from Science to Policy: Evidence from Overton data

引用

Proceedings of the Association for Information Science and Technology 2023年第1期60卷 368-378页

作者： Ren, Chao Yang, Menghui School of Information Resource Management Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China

The cross-domain knowledge diffusion from science to policy is a prevalent phenomenon that demands academic attention. To investigate the characteristics of cross-domain knowledge diffusion from science to policy, this study suggests using the citation of policies to scientific articles as a basis for quantifying the diffusion strength, breadth, and speed. The study reveals that the strength and breadth of cross-domain knowledge diffusion from scientific papers to policies conform to a power-law distribution, while the speed follows a logarithmic normal distribution. Moreover, the papers with the highest diffusion strength, breadth, and fastest diffusion speed are predominantly from world-renowned universities, scholars, and top journals. The papers with the highest diffusion strength and breadth are mostly from social sciences, especially economics, those with the fastest diffusion speed are mainly from medical and life sciences, followed by social sciences. The findings indicate that cross-domain knowledge diffusion from science to policy follows the Matthew effect, whereby individuals or institutions with high academic achievements are more likely to achieve successful cross-domain knowledge diffusion. Furthermore, papers in the field of economics tend to have the higher cross-domain knowledge diffusion strength and breadth, while those in medical and life sciences have the faster cross-domain knowledge diffusion speed. 86 Annual Meeting of the Association for Information Science & Technology | Oct. 27 – 31, 2023 | London, United Kingdom. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Hadamard Encoding Based Frequent Itemset Mining under Local Differential Privacy

引用

Journal of Computer Science & Technology 2023年第6期38卷 1403-1422页

作者：赵丹赵素云陈红刘睿瑄李翠平张晓莹 Institute of Scientific and Technical Information of China Beijing 100038China Key Laboratory of Data Engineering and Knowledge Engineering(Ministry of Education) School of InformationRenmin University of ChinaBeijing 100872China

Local differential privacy(LDP)approaches to collecting sensitive information for frequent itemset mining(FIM)can reliably guarantee *** current approaches to FIM under LDP add"padding and sampling"steps to obtain frequent itemsets and their frequencies because each user transaction represents a set of *** current state-of-the-art approach,namely set-value itemset mining(SVSM),must balance variance and bias to achieve accurate ***,an unbiased FIM approach with lower variance is highly *** narrow this gap,we propose an Item-Level LDP frequency oracle approach,named the Integrated-with-Hadamard-Transform-Based Frequency Oracle(IHFO).For the first time,Hadamard encoding is introduced to a set of values to encode all items into a fixed vector,and perturbation can be subsequently applied to the *** FIM approach,called optimized united itemset mining(O-UISM),is pro-posed to combine the padding-and-sampling-based frequency oracle(PSFO)and the IHFO into a framework for acquiring accurate frequent itemsets with their ***,we theoretically and experimentally demonstrate that O-UISM significantly outperforms the extant approaches in finding frequent itemsets and estimating their frequencies under the same privacy guarantee.

关键词： local differential privacy frequent itemset mining frequency oracle

来源：评论

学校读者我要写书评

暂无评论

Leaving None Behind: data-Free Domain Incremental Learning for Major Depressive Disorder Detection

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 758-770页

作者： Chen, Tao Guo, Yanrong Hao, Shijie Hong, Richang Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data China Hefei University of Technology Ministry of Education and School of Computer Science and Information Engineering Hefei230009 China

While deep learning techniques have shown promising performance in the Major Depressive Disorder (MDD) detection task, they still face limitations in real-world scenarios. Specifically, given the data scarcity, some efforts have resorted to aggregating data from different domains to expand the data volume. However, their effectiveness is currently limited by the domain gap and data privacy. Additionally, the class imbalance issue is particularly severe in our application, leading to biased classifying performance accordingly. To address these challenges, we propose data-Free Domain Incremental Learning for the MDD detection (DIL-MDD) task, accommodating multiple feature distributions by only accessing well-trained models from previous domains and the data in the current domain. Specifically, DIL-MDD consists of two key modules: Adaptive Class-tailored Threshold Learning (ACTL) and data-Free Domain Alignment (DFDA). The first module measures the discrepancy between the outputs of two sequential domains, based on which we learn a class-tailored threshold adaptively. Building on this, we differentiate between samples that either exhibit similarities or dissimilarities with the previous domain, where this similar sample set is identified to investigate the feature distribution of the historical data. The second module imposes an alignment constraint to narrow the gap between these two sample sets, thereby exploring the expertise of the previous domain. To validate the effectiveness of the proposed method, we conduct extensive experiments on the public MDD datasets, i.e., DAIC-WOZ, MODMA, and CMDC. We also apply our method to another mental health condition, Autism Spectrum Disorder (ASD), to further demonstrate its applicability. Finally, the ablation studies validate the superiority of the proposed modules. © 2010-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Cross-Modal Fusion Based Refinement for Text-to-Image Synthesis

引用

Chinese Journal of Electronics 2023年第6期32卷 1329-1340页

作者： SUN Haoran WANG Yang LIU Haipeng QIAN Biao Department of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of EducationHefei University of Technology

Text-to-image synthesis refers to generating visual-realistic and semantically consistent images from given textual descriptions. Previous approaches generate an initial low-resolution image and then refine it to be high-resolution. Despite the remarkable progress, these methods are limited in fully utilizing the given texts and could generate text-mismatched images, especially when the text description is complex. We propose a novel finegrained text-image fusion based generative adversarial networks(FF-GAN), which consists of two modules: Finegrained text-image fusion block(FF-Block) and global semantic refinement(GSR). The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details. And the GSR is proposed to improve the global semantic consistency between linguistic and visual features during the refinement process. Extensive experiments on CUB-200 and COCO datasets demonstrate the superiority of FF-GAN over other state-of-the-art approaches in generating images with semantic consistency to the given texts.

关键词： Visualization Fuses Convolution Semantics Linguistics Benchmark testing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Dual-stream coupling network with wavelet transform for cross-resolution person re-identification

引用

Journal of Systems engineering and Electronics 2023年第3期34卷 682-695页

作者： SUN Rui YANG Zi ZHAO Zhenghui ZHANG Xudong Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education) Hefei University of TechnologyHefei 230601China School of Computer and Information Hefei University of TechnologyHefei 230601China

Person re-identification is a prevalent technology deployed on intelligent *** have been remarkable achievements in person re-identification methods based on the assumption that all person images have a sufficiently high resolution,yet such models are not applicable to the open *** real world,the changing distance between pedestrians and the camera renders the resolution of pedestrians captured by the camera *** low-resolution(LR)images in the query set are matched with high-resolution(HR)images in the gallery set,it degrades the performance of the pedestrian matching task due to the absent pedestrian critical information in LR *** address the above issues,we present a dualstream coupling network with wavelet transform(DSCWT)for the cross-resolution person re-identification ***,we use the multi-resolution analysis principle of wavelet transform to separately process the low-frequency and high-frequency regions of LR images,which is applied to restore the lost detail information of LR ***,we devise a residual knowledge constrained loss function that transfers knowledge between the two streams of LR images and HR images for accessing pedestrian invariant features at various *** qualitative and quantitative experiments across four benchmark datasets verify the superiority of the proposed approach.

关键词： cross-resolution feature invariant learning person re-identification residual knowledge transfer wavelet transform

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adaptation

引用

data Intelligence 2024年第1期6卷 183-200页

作者： Yuhong Zhang Jianqing Wu Qi Zhang Xuegang Hu School of Computer and Information Engineering Hefei University of TechnologyHefei 230601China Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) The Ministry of Education of ChinaHefei 230009China

Domain adaptation aims to transfer knowledge from the labeled source domain to an unlabeled target domain that follows a similar but different ***,adversarial-based methods have achieved remarkable success due to the excellent performance of domain-invariant feature presentation ***,the adversarial methods learn the transferability at the expense of the discriminability in feature representation,leading to low generalization to the target *** this end,we propose a Multi-view Feature Learning method for the Over-penalty in Adversarial Domain ***,multi-view representation learning is proposed to enrich the discriminative information contained in domain-invariant feature representation,which will counter the over-penalty for discriminability in adversarial ***,the class distribution in the intra-domain is proposed to replace that in the inter-domain to capture more discriminative information in the learning of transferrable *** experiments show that our method can improve the discriminability while maintaining transferability and exceeds the most advanced methods in the domain adaptation benchmark datasets.

关键词： domain adaptation adversarial learning multi-view learning

来源：评论

学校读者我要写书评

暂无评论

Diversifying Question Generation over knowledge Base via External Natural Questions 30

Diversifying Question Generation over Knowledge Base via Ext...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Guo, Shasha Zhang, Jing Ke, Xirui Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China

ISBN: (纸本)9782493814104

Previous methods on knowledge base question generation (KBQG) primarily focus on refining the quality of a single generated question. However, considering the remarkable paraphrasing ability of humans, we believe that diverse texts can express identical semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the aforementioned diversity. They calculate the ratio of unique n-grams in the generated question, which tends to measure duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG show that our approach can outperform pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

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：