检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Huang, Yifei Cao, Jingxin Luo, Hanyu Guan, Xin Liu, Bo School of Cyber Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information of Ministry of Education of China Nanjing211189 China School of Computer Science and Engineering Southeast University Nanjing211189 China

ISBN: (纸本)9798891761964

With the quick advancement in text generation ability of Large Language Model(LLM), concerns about the misuse of machine-generated text(MGT) have grown, raising potential violations of legal and ethical standards. Some existing studies concentrate on detecting machine-generated text in open-source models using in-model features, but their performance on closed-source large models is limited. This limitation occurs because, in the closed-source model detection, the only reference that can be obtained is the texts, which may differ significantly due to random sampling. In this paper, we demonstrate that texts generated by the same model can align both semantically and statistically under similar prompts, facilitating effective detection and traceability. Specifically, we fine-tune a BERT encoder through contrastive learning to achieve semantic alignment in randomly generated texts from the same model. Then, we propose a method called Machine-Generated Text Detection with Rewritten Texts, which designed several prompt refactoring methods and used them to request rewritten text from LLMs. Semantic and statistical relationships between rewritten and original texts provide a basis for detection and traceability. Finally, we expanded the text dataset with multi-parameter random sampling and verified the performance of MAGRET on three text-generated datasets. Experimental results show that previous methods struggle with closed-source model detection, while our approach significantly outperforms baseline methods in this regard. It also shows MAGRET's stable performance in detection and tracing tasks across various randomly sampled texts. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised temporal action localization with proxy metric modeling

引用

Frontiers of computer science 2023年第2期17卷 63-72页

作者： Hongsheng XU Zihan CHEN Yu ZHANG Xin GENG Siya MI Zhihong YANG NARI Group Corporation(State Grid Electric Power Research Institute) Nanjing 211106China School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China School of Cyber Science and Engineering Southeast UniversityNanjing 211189China Purple Mountain Laboratories Nanjing 211111China

Temporal localization is crucial for action video *** the manual annotations are expensive and time-consuming in videos,temporal localization with weak video-level labels is challenging but *** this paper,we propose a weakly-supervised temporal action localization approach in untrimmed *** settle this issue,we train the model based on the proxies of each action *** proxies are used to measure the distances between action segments and different original action *** use a proxy-based metric to cluster the same actions together and separate actions from *** with state-of-the-art methods,our method achieved competitive results on the THUMOS14 and ActivityNet1.2 datasets.

关键词： temporal action localization weakly supervised videos proxy metric

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning 30

Few-Shot Semantic Dependency Parsing via Graph Contrastive L...

引用

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

作者： Li, Bin Fan, Yunlong Sataer, Yikemaiti Shi, Chuanqi Gao, Miao Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education China

ISBN: (纸本)9782493814104

Graph neural networks (GNNs) have achieved promising performance on semantic dependency parsing (SDP), owing to their powerful graph representation learning ability. However, training a high-performing GNN-based model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labeled data. To address this drawback, we propose a syntax-guided graph contrastive learning framework to pre-train GNNs with plenty of unlabeled data and fine-tune pre-trained GNNs with few-shot labeled SDP data. Through extensive experiments conducted on the SemEval-2015 Task 18 English dataset in three formalisms (DM, PAS, and PSD), we demonstrate that our framework achieves promising results when few-shot training samples are available. Furthermore, benefiting from the pre-training process, our framework exhibits notable advantages in the out-of-domain test sets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Parameter-Efficient Transformers with Contrastive Syntax and Regularized Dropout for Neural Machine Translation 21st

Enhancing Parameter-Efficient Transformers with Contrastive...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Fan, Yunlong Yang, Zhiheng Li, Baixuan Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9789819601219

Transformers have significantly improved Neural Machine Translation (NMT) models, accompanied by the inherent space complexity of O(n2). While recent approaches aim to be parameter-efficient, they often exhibit limited generalization capabilities with fewer parameters and decreased performances in longer sentences. To this end, we propose two methods, Syntax-enhanced Contrastive Learning (Syn-CL) and JS divergence-based Regularized Dropout (JSR-Drop) for the cross-layer parameter-sharing Transformer (baseline) in NMT. In Syn-CL, we add the corresponding target-to-source instances for the same batch in an extra bidirectional training phase, and minimize the distances of syntax-enhanced representation between the bilingual sentence-pair while maximizing the ones among others. In JSR-Drop, we refine the regularized dropout strategy with JS divergence, and improve generalization capabilities by reducing Transformers’ inconsistencies between training and inference introduced by dropout. Extensive experiments on six NMT tasks, IWSLT2014 (German↔English) and IWSLT2017 (English↔French and English↔Romanian), show an average BLEU score of 37.55, surpassing the vanilla Transformer and the baseline up to 1.75 BLEU, and outperforming models with 1.5×, 2.0× parameters in translating long sentences. Our code is available at https://***/Anon1214/EnPeNMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Resource Cooperative Scheduling Optimization Considering Security in Edge Mobile networks 19th

Resource Cooperative Scheduling Optimization Considering Sec...

引用

19th EAI International Conference on Collaborative Computing: networking, Applications and Worksharing, CollaborateCom 2023

作者： Fang, Cheng Yang, Peng Yi, Meng Du, Miao Li, Bing Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9783031545207

With the rapid development of technologies such as the Internet of Things and artificial intelligence, the contradiction between limited user computing resources and real-time, fast, and safe processing of large amounts of data has become an urgent issue. The emergence of edge computing provides IoT applications with a low-latency, high-bandwidth, and high-performance computing service. Due to the complexity and dynamics of the edge computing environment itself, and the limited resources of the terminal, the security issue of resource collaborative scheduling in the edge mobile network has become an important research topic. Different from existing work, this paper proposes an efficient and secure multi-user resource cooperative scheduling model, which comprehensively considers resource allocation, task offloading, QoE requirements, and data security. In the model, ChaCha20 encryption technology is introduced as a security mechanism to prevent data from being maliciously stolen by attackers during the offloading process, and computing speed is used as an indicator to quantify QoE requirements. A resource collaborative scheduling algorithm that integrates security mechanisms and computing acceleration is also proposed to minimize the total cost of optimizing the edge computing system. Finally, the effectiveness and superiority of the model and algorithm are verified by simulation experiments. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A survey on event connections and their discovery for cloud service

A survey on event connections and their discovery for cloud ...

引用

2023 International Conference on Electronic Information engineering and Data Processing, EIEDP 2023

作者： Zhang, Zhen Xia, Chunhe Li, Shuyu Liu, Zhiying Huang, Mingzhi Huang, Chengling Li, Xiaojian School of Computer Science & Engineering Guangxi Normal University Guilin China Beijing Key Laboratory of Network Technology School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781510666160

Connection is the effect between events. It is an important basis for judging of violations and source-trace of failure in cloud service accountability. This paper presents a survey on the event connections including the features, method of discovery and correction. Most of recent research on event connections in cloud services relying on manually labeling and correcting to event connections, and a few of them have achieved automatically labeling of event connections. Finally, we give out a taxonomy of the recent research, some problems in the method of discovery and correction, and an approach in the paper. © 2023 SPIE.

关键词： Distributed database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Self-perception Enhanced Large Language Model for 3D Region-of-Interest Captioning with Limited Data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University and the Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing100044 China Central South University School of Computer Science and Engineering Hunan Changsha0410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer and lnformation Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

A novel coarse-grained knowledge graph embedding framework for platform risk identification from relational data

引用

Neural Computing and Applications 2025年 1-21页

作者： Zhang, Qi Wang, Shicheng Wang, Lihong Sheng, Jiawei Guo, Shu Li, Chen He, Min Zhang, Renqiang School of Economics and Management Beihang University Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China School of Computer Science and Engineering Beihang University Beijing China

Platform risk identification from relational data aims to determine whether the target platforms are risky or not. However, in such a scenario, the relation data involve massive types of relations and numerous numerical-aware relations composed of attributes and infinite continuous values are challenges in this field. It is paramount to capture semantic information of relations and precise control power, drastically affecting the power of learning and the performance of identifying risky platforms. Recent financial risk studies often employed graph neural networks (GNNs) to model relational data, which fall short of capturing the intricacies of such complex relationships resulting in incorrect identification of platforms. To solve this problem, we propose a novel coarse-grained knowledge graph embedding (CKGE) framework that integrates coarse-grained knowledge graph construction and adopts five well-known knowledge graph embedding methods and ensemble learning. The extensive experimental results based on a real-world peer-to-peer lending platform dataset demonstrate that the CKGE framework achieves state of the art over GNNs for platform risk identification. Our study highlights the importance of utilizing the relational data of multi-type and multi-numerical relations for revealing platform risk situations and provides an alternative solution for identifying platform risk. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SDDNet:Infrared small and dim target detection network

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1226-1236页

作者： Ma Long Shu Cong Huang Shanshan Wei Zoujian Wang Xuhao Wei Yanxi School of Computer Science and Engineering Xi'an Technological UniversityXi'anShaanxiChina State and Local Joint Laboratory of Advanced Network and Monitoring Xi'anShaanxiChina School of Computing University of Kent CanterburyUK

This study focuses on developing deep learning methods for small and dim target *** model infrared images as the union of the target region and background *** on this model,the target detection problem is considered a two‐class segmentation problem that divides an image into the target and ***,a neural network called SDDNet for single‐frame images is *** network yields target extraction results according to the original *** multiframe images,a network called IC‐SDDNet,a combination of SDDNet and an interframe correlation network module is *** and IC‐SDDNet achieve target detection rates close to 1 on typical datasets with very low false positives,thereby performing significantly better than current *** models can be executed end to end,so both are very convenient to use,and their implementation efficiency is very *** speeds of 540+/230+FPS and 170+/60+FPS are achieved with SDDNet and IC‐SDDNet on a single Tesla V100 graphics processing unit and a single Jetson TX2 embedded module ***,neither network needs to use future information,so both networks can be directly used in real‐time *** well‐trained models and codes used in this study are available at https://***/LittlePieces/ObjectDetection.

关键词： deep learning detection of moving objects

来源：评论

学校读者我要写书评

暂无评论

Research on Machine Unlearning Verification Based on Predictive Cross-Entropy 10

Research on Machine Unlearning Verification Based on Predict...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Yue, Xinghui Peng, Jiale Liu, Meiqi He, Haitao Zhang, Yuqing YanShan University & National Computer Network Intrusion Prevention Center University of Chinese Academy of Sciences School of Information Science and Engineering Hebei China YanShan University School of Information Science and Engineering Hebei China YanShan University & National Computer Network Intrusion Prevention Center University of Chinese Academy of Sciences School of Information Science and Engineering Hebei Beijing China

ISBN: (纸本)9798331520861

The General Data Protection Regulation (GDPR), implemented by the European Union in 2018, set a global standard for personal data privacy protection. Among its requirements is the 'right to be forgotten' which mandates that service providers must delete a user's personal data upon the user's request to withdraw data authorization. However, deep learning networks tend to retain learned information, making them susceptible to privacy attacks. While several methods exist for achieving machine unlearning to enforce the right to be forgotten, verifying the effectiveness of machine unlearning remains challenging. In this paper, we propose the metric 'Percentage of Unlearning' (PoU), which measures the extent of machine unlearning through the change in predictive cross-entropy of the data intended to be forgotten during the unlearning process. We introduce a machine unlearning verification framework based on predictive cross-entropy, enabling users to self-verify whether their data has been deleted without solely relying on the service providers' assurances. This framework also assists service providers in ensuring complete machine unlearning while minimizing time and computational costs. We compared the PoU metric with existing verification metrics such as ACC and MIA recall. Experimental results demonstrate that, compared to existing verification methods, the PoU metric not only confirms the effectiveness of machine unlearning but also addresses the shortcomings of existing metrics by quantifying the degree of unlearning. © 2024 IEEE.

关键词： Differential privacy

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：