检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhao, Haofei Liu, Yilun Tao, Shimin Meng, Weibin Chen, Yimeng Geng, Xiang Su, Chang Zhang, Min Yang, Hao School of Computer Science and Engineering Northeastern University Shenyang China Huawei China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT. After two decades of evolution, QE has yielded a wealth of results. This article provides a comprehensive overview of QE datasets, annotation methods, shared tasks, methodologies, challenges, and future research directions. It begins with an introduction to the background and significance of QE, followed by an explanation of the concepts and evaluation metrics for word-level QE, sentence-level QE, document-level QE, and explainable QE. The paper categorizes the methods developed throughout the history of QE into those based on handcrafted features, deep learning, and Large Language Models (LLMs), with a further division of deep learning-based methods into classic deep learning and those incorporating pre-trained language models (LMs). Additionally, the article details the advantages and limitations of each method and offers a straightforward comparison of different approaches. Finally, the paper discusses the current challenges in QE research and provides an outlook on future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Akane: Perplexity-Guided Time Series Data Cleaning

引用

Proceedings of the ACM on Management of Data 2024年第3期2卷 1-26页

作者： Xiaoyu Han Haoran Xiong Zhenying He Peng Wang Chen Wang X. Sean Wang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China National Engineering Research Center for Big Data Software EIRI Tsinghua University Beijing China

Dirty data are prevalent in time series, such as energy consumption or stock data. Existing data cleaning algorithms present shortcomings in dirty data identification and unsatisfactory cleaning decisions. To handle these drawbacks, we leverage inherent recurrent patterns in time series, analogize them as fixed combinations in textual data, and incorporate the concept of perplexity. The cleaning problem is thus transformed to minimize the perplexity of the time series under a given cleaning cost, and we design a four-phase algorithmic framework to tackle this problem. To ensure the framework's feasibility, we also conduct a brief analysis of the impact of dirty data and devise an automatic budget selection strategy. Moreover, to make it more generic, we additionally introduce advanced solutions, including an ameliorative probability calculation method grounded in the homomorphic pattern aggregation and a greedy-based heuristic algorithm for resource savings. Experiments on 12 real-world datasets demonstrate the superiority of our methods.

关键词： data cleaning perplexity recurrent patterns time series

来源：评论

学校读者我要写书评

暂无评论

Causal and Local Correlations Based Network for Multivariate Time Series Classification

arXiv

引用

arXiv 2024年

作者： Du, Mingsen Wei, Yanxuan Zheng, Xiangwei Ji, Cun School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China

Recently, time series classification has attracted the attention of a large number of researchers, and hundreds of methods have been proposed. However, these methods often ignore the spatial correlations among dimensions and the local correlations among features. To address this issue, the causal and local correlations based network (CaLoNet) is proposed in this study for multivariate time series classification. First, pairwise spatial correlations between dimensions are modeled using causality modeling to obtain the graph structure. Then, a relationship extraction network is used to fuse local correlations to obtain long-term dependency features. Finally, the graph structure and long-term dependency features are integrated into the graph neural network. Experiments on the UEA datasets show that CaLoNet can obtain competitive performance compared with state-of-the-art methods. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Keep It Simple: Towards Accurate Vulnerability Detection for Large Code Graphs

arXiv

引用

arXiv 2024年

作者： Peng, Xin Wang, Shangwen Qin, Yihao Lin, Bo Chen, Liqian Mao, Xiaoguang Cheng, Jieren The Key Laboratory of Software Engineering for Complex Systems College of Computer Science and Technology National University of Defense Technology Changsha China The Hainan University Haikou China

software vulnerability detection is crucial for high-quality software development. Recently, some studies utilizing Graph Neural Networks (GNNs) to learn the graph representation of code in vulnerability detection tasks have achieved remarkable success. However, existing graph-based approaches mainly face two limitations that prevent them from generalizing well to large code graphs: (1) the interference of noise information in the code graph;(2) the difficulty in capturing long-distance dependencies within the graph. To mitigate these problems, we propose a novel vulnerability detection method, ANGEL, whose novelty mainly embodies the hierarchical graph refinement and context-aware graph representation learning. The former hierarchically filters redundant information in the code graph, thereby reducing the size of the graph, while the latter collaboratively employs the Graph Transformer and GNN to learn code graph representations from both the global and local perspectives, thus capturing long-distance dependencies. Extensive experiments demonstrate promising results on three widely used benchmark datasets: our method significantly outperforms several other baselines in terms of the accuracy and F1 score. Particularly, in large code graphs, ANGEL achieves an improvement in accuracy of 34.27%-161.93% compared to the state-of-the-art method, AMPLE. Such results demonstrate the effectiveness of ANGEL in vulnerability detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Embedding Representation of Academic Heterogeneous Information Networks Based on Federated Learning 8

Embedding Representation of Academic Heterogeneous Informati...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Wang, Junfu Li, Yawen Liang, Meiyu Li, Ang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing100876 China Beijing University of Posts and Telecommunications School of Economics and Management Beijing China

ISBN: (纸本)9781665477352

Existing studies for representation learning of homogeneous information networks cannot be applicable to academic heterogeneous information networks (HINs) with multi-type nodes and multi-relationships because of the lack of ability to issue heterogeneity. Meanwhile, due to the closeness and blocking of businesses among different enterprises, there is a serious phenomenon of data islands. To solve the above challenges, we proposed an academic heterogeneous information network embedding representation learning method based on federated learning (FedAHE), which utilizes node attention and meta path attention mechanism to learn low-dimensional, dense and real-valued vector representations while preserving the rich topological information and meta-path-based semantic information of nodes in network. Moreover, we combined federated learning with the representation learning of academic HINs and put forward a federal training mechanism based on dynamic weighted aggregation of parameters (FedDWA) to optimize the node embeddings of HINs. Through sufficient experiments, the efficiency, accuracy and feasibility of our proposed framework are demonstrated. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Explainable AI: A Way to Achieve Trustworthy AI

Explainable AI: A Way to Achieve Trustworthy AI

引用

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart Computing (HPSC) and Intelligent Data and Security (IDS)

作者： Yanlu Li Yufeng Xiao Yinyan Gong Ronglin Zhang Yingzi Huo Yanbing Wu Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798350389524

ISBN: (纸本)9798350389531

AI is black-box and non-explainable, in other words, due to the complexity of the decision-making process of AI, people are unable to know why and how AI makes the decision. For these reasons, people will question and worry about AI’s decision-making. Against this background, researchers have proposed the concept of Explainable Artificial Intelligence (XAI). The aim of this paper is to help readers be able to better understand XAI through extensive surveys. In this paper, we discuss the concept of XAI, the motivation of the research, the current status of the research, and the difficulties in the research process. At the same time, we also discuss the specific methods to realize AI explainability by dividing AI explainability methods into two ways: transparent design and ex post facto interpretation. In addition, we select the three fields of healthcare, finance, and autonomous driving, discuss the application of XAI in these three fields, and select some representative results as examples through surveys. Finally, we summarize this article and present our outlook on the future development of XAI.

关键词： Surveys Explainable AI Decision making Finance Closed box Medical services Big Data

来源：评论

学校读者我要写书评

暂无评论

From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation

From Handcrafted Features to LLMs: A Brief Survey for Machin...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Haofei Zhao Yilun Liu Shimin Tao Weibin Meng Yimeng Chen Xiang Geng Chang Su Min Zhang Hao Yang Shool of Computer Science and Engineering Northeastern University Shenyang China Huawei China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

关键词： Deep learning Learning systems Surveys Measurement Annotations Neural networks Estimation

来源：评论

学校读者我要写书评

暂无评论

SeaCap: Multi-Sight Embedding and Alignment for One-Stage Image Captioner

引用

IEEE Transactions on Multimedia 2025年 27卷 3411-3425页

作者： Wang, Bo Zhang, Zhao Zhao, Mingbo Jin, Xiaojie Xu, Mingliang Wang, Meng Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Yunnan Key Laboratory of Software Engineering Yunan China Donghua University School of Computer Science and Engineering Shanghai201620 China ByteDance Culver CityCA90230 United States Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China

Recent mainstream image captioning methods usually adopt two-stage captioners, i.e., calculating the object features of the given image by a pre-trained detector and then feeding them into a language model to generate the descriptive sentences. However, such a two-stage procedure will lead to a task-based information gap that decreases the performance of the captioners, because the object features learned from the detection task are suboptimal representations and cannot provide all the necessary information for subsequent sentence generation. Besides, the object features are usually represented by the last pooling features of the detector that lose the local details of images. In this paper, we propose a novel One-Stage Image Captioner using dynamic multi-sight embedding and alignment, called SeaCap, which directly transforms input images into descriptive sentences in one stage to eliminate the information gap. Specifically, to obtain rich features, we use the Swin Transformer to capture multi-level features, followed by a sights alignment module to alleviate the vision confusion, and then feed them into a novel dynamic multi-sight embedding module to exploit both the global structure and local texture of input images. To enhance the global modeling capacity of the visual encoder, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. As a result, SeaCap can obtain rich and useful information to improve the performance of the captioner. Extensive comparisons on the benchmark MS-COCO, Flickr8K and Flickr30 K datasets verified the superior performance of our method. © 1999-2012 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Series

arXiv

引用

arXiv 2024年

作者： Yu, Zhihao Chu, Xu Ma, Liantao Wang, Yasha Zhu, Wenwu Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China School of Computer Science Peking University Beijing China Department of Computer Science Tsinghua University Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China

Irregularly sampled time series are ubiquitous, presenting significant challenges for analysis due to missing values. Despite existing methods address imputation, they predominantly focus on leveraging intra-series information, neglecting the potential benefits that inter-series information could provide, such as reducing uncertainty and memorization effect. To bridge this gap, we propose PRIME, a Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series. Our framework comprises a prototype memory module for learning inter-series information, a bidirectional gated recurrent unit utilizing prototype information for imputation, and an attentive prototypical refinement module for adjusting imputations. We conducted extensive experiments on three datasets, and the results underscore PRIME’s superiority over the state-of-the-art models by up to 26% relative improvement on mean square error. Our code is available at https://***/yzhHoward/PRIME. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Time series classification based on Unet with 2D transformation

Time series classification based on Unet with 2D transformat...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Mingsen Du Yunxia Wang Yanxuan Wei Xiaona Wu Cun Ji School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China

ISBN: (数字)9798331510633

ISBN: (纸本)9798331510640

Time series classification has gained significant attention in the data mining field in recent years. Despite the proposal of numerous methods over the past decades, most of these approaches focus on feature extraction in one-dimensional space, which often results in lower classification accuracy. To address this issue, this paper proposes a Time Series Classification method based on U-Net with 2D transformation (TSC-Unet). This method first transforms univariate time series into 2D space and augments the data, effectively enhancing the diversity of the dataset. Subsequently, features are extracted from the 2D space using a fully convolutional network, fully exploiting multi-scale feature information. U-Netwith skip connections, effectively retains and transmits high-resolution features, significantly reducing information loss and improving segmentation performance. Additionally, the ability to learn multi-scale features enables the model to capture details at different levels, thereby enhancing its understanding of complex data. Experimental results demonstrate that TSC-Unet achieves high classification accuracy on the UCR datasets, validating the effectiveness and superiority of the proposed method.

关键词： Accuracy Time series analysis Transforms Feature extraction Propagation losses Data models Data mining Convolutional neural networks Proposals Internet of Things

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：