检索结果-内蒙古大学图书馆

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

作者： Zhang, Zhiheng Zeng, Daojian Bai, Xue Institute of AI and Targeted International Communication Hunan Normal University Changsha China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Changsha Dworld AI Tech Co. Ltd. China

ISBN: (纸本)9782493814104

In this paper, we focus on the challenging yet practical problem of Continual Few-shot Relation Extraction (CFRE), which involves extracting relations in the continuous and iterative arrival of new data with only a few labeled examples. The main challenges in CFRE are overfitting due to few-shot learning and catastrophic forgetting caused by continual learning. To address these problems, we propose a novel framework called RK2DA, which seamlessly integrates prototype-based data augmentation and relational knowledge distillation. Specifically, RK2DA generates pseudo data by introducing Gaussian noise to the prototype embeddings and utilizes a novel two-phase multi-teacher relational knowledge distillation method to transfer diverse knowledge from different embedding spaces. Experimental results on the FewRel and TACRED datasets demonstrate that our method outperforms the state-of-the-art baselines. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: Predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: Predicting drug-target interaction through cross-v...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xuan Zhang, Xi Yu, Zu-Guo Long, Yahui Zeng, Xiangxiang Yu, Philip S. Xiangtan University College of Computer Science China Xiangtan University Key Laboratory of Intelligent Computing and Information Processing Ministry of Education China Singapore Hunan University College of Information Science and Engineering China University of Illinois Chicago Department of Computer Science United States

ISBN: (纸本)9798350386226

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI1 outperforms six state-of-the-art methods. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Emotional Knowledge Self-Distillation in Dialogue

Emotional Knowledge Self-Distillation in Dialogue

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jian, Zhongquan Wang, Yancheng Wu, Weichao Yao, Junfeng Wang, Meihong Wu, Qingqiang School of Informatics Xiamen University Xiamen China School of Film Xiamen University Xiamen China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of Mechanics and Civil Engineering China University of Mining & Technology Beijing China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen China

ISBN: (纸本)9798350368741

Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in Natural Language processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) have primarily focused on contextual features, while overlooking the importance of emotional features in emotion recognition. To address this gap, we focus on the role of emotional features in ERC and propose a novel method, Emotional Knowledge Self-Distillation (EmoKSD1), to enhance the model's emotional sensitivity. In EmoKSD, utterances are enriched with implicit 〈mask〉 tokens to represent conveyed emotions, allowing the distillation of emotional knowledge from explicit emotional tokens to implicit 〈mask〉 tokens, thereby enhancing the model's ability to perceive subtle emotions within the dialogue. Through thorough evaluations on two public ERC datasets (i.e., IEMOCAP and MELD) using proposed coarse-grained utterance distillation and fine-grained token distillation techniques, EmoKSD demonstrates superior performance compared to existing methods, highlighting the significance of emotional features in ERC. © 2025 IEEE.

关键词： Dialogue System Emotion Recognition in Conversation Knowledge Distillation Natural Language processing

来源：评论

学校读者我要写书评

暂无评论

CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images

CMA: A Chromaticity Map Adapter for Robust Detection of Scre...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changsheng Chen Liangwei Lin Yongqi Chen Bin Li Jishen Zeng Jiwu Huang Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Alibaba Group Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen MSU-BIT University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The rebroadcasting of screen-recaptured document images introduces a significant risk to the confidential docu-ments processed in government departments and commer-cial companies. However, detecting recaptured document images subjected to distortions from online social networks (OSNs) is challenging since the common forensics cues, such as moiré pattern, are weakened during transmission. In this work, we first devise a pixel-level distortion model of the screen-recaptured document image to identify the robust features of color artifacts. Then, we extract a chromaticity map from the recaptured image to highlight the presence of color artifacts even under low-quality samples. Based on the prior understanding, we design a chromaticity map adapter (CMA) to efficiently extract the chromaticity map, and feed it into the transformer backbone as multi-modal prompt tokens. To evaluate the performance of the pro-posed method, we collect a recaptured office document im-age dataset with over 10K diverse samples. Experimental results demonstrate that the proposed CMA method outper-forms a SOTA approach (with RGB modality only), reducing the average EER from 26.82% to 16.78%. Robustness eval-uation shows that our method achieves 0.8688 and 0.7554 AUCs under samples with JPEG compression $(QF=70)$ and resolution as low as $534\times 503$ pixels.

关键词： Image color analysis Social networking (online) Forensics Splicing Transform coding Feature extraction Distortion

来源：评论

学校读者我要写书评

暂无评论

Research on patent classification based on hierarchical label semantics 3

Research on patent classification based on hierarchical labe...

引用

3rd International Conference on Education, Knowledge and Information Management, ICEKIM 2022

作者： Chen, Jie Zhao, Shu Lu, Fan Liu, Feng Zhang, Yangping Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui University School of Computer Science and Technology Hefei China

ISBN: (纸本)9781665416665

Patent classification is an essential task in patent information management and knowledge mining. Most existing studies are based on the textual content of individual patent texts (e.g., titles and abstracts) for classification, but the patent also has label information with hierarchical structure and semantic description. However, the semantics correlation of patent texts and their labels have been largely ignored. In this paper, we propose a novel framework called HLSPC for patent classification by leveraging the hierarchical semantics correlation of patent texts and their labels. Specifically, we first apply a patent representation learning module for capturing the semantics representation of patent texts and hierarchical labels. Then, we design a label attention learning module to build the semantics correlation between patent texts and hierarchical labels, which enhances patent representation. Finally, we deploy a multi-level fusion module to get the refined category prediction for each patent which can preserve both local and global hierarchical prediction information. Extensive experimental results on two English patent datasets demonstrate the effective power of the HLSPC model. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Virtual Machine Placement Algorithm Based on Improved Grouping GA

An Energy-Efficient Virtual Machine Placement Algorithm Base...

引用

IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE)

作者： Taisheng Zeng Xiaodong Wu School of Mathematics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Quanzhou China

ISBN: (数字)9798350377033

ISBN: (纸本)9798350377040

Virtual machine placement (VMP) plays a crucial role in optimizing the efficiency and sustainability of data centers. By consolidating virtual machines (VMs) onto fewer physical machines (PMs), VMP can significantly reduce power consumption and enhance resource utilization. This not only leads to cost savings but also contributes to environmental sustainability by minimizing energy waste. This paper focuses on addressing the energy-efficient VMP problem, which is critical for modern data centers aiming to balance performance and energy consumption. To tackle this challenge, we propose an improved group-based genetic algorithm (GGA). The GGA employs a novel grouping approach to encode chromosomes, allowing for more effective representation of VM-to-PM assignments. Additionally, optimized crossover and mutation operators are designed to improve the algorithm's performance, ensuring faster convergence and better solutions. Experimental results demonstrate that the proposed algorithm outperforms traditional algorithms in terms of energy-saving efficiency and convergence speed.

关键词： Data centers Power demand Virtual machines Energy efficiency Resource management Sustainable development Biological cells Optimization Genetic algorithms Convergence

来源：评论

学校读者我要写书评

暂无评论

M3GPT: an advanced multimodal, multitask framework for motion comprehension and generation 24

M3GPT: an advanced multimodal, multitask framework for motio...

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Mingshuang Luo Ruibing Hou Zhuo Li Hong Chang Zimo Liu Yaowei Wang Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China and Peng Cheng Laboratory China and University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China WeChat Tencent Inc Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China and University of Chinese Academy of Sciences China Peng Cheng Laboratory China Peng Cheng Laboratory China and Harbin Institute of Technology Shenzhen

ISBN: (纸本)9798331314385

This paper presents M3 GPT, an advanced Multimodal, Multitask framework for Motion comprehension and generation. M3 GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M3 GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M3 GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M3GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: https://***/M3GPT/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A framework for Chinese event semantic constraint predicates and their generation using PEFT LLM and RAG

引用

International Journal of Machine Learning and Cybernetics 2025年

作者： Huang, Qiaojuan Wang, Shi He, Qing Cao, Cungen Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Event semantic analysis is a crucial area of research in natural language processing. It focuses on deeply understanding the semantics of events and their components. While existing semantic frameworks and event semantic labelling cover a wealth of semantic information, further research is needed to explore the fine-grained semantic relationships across participants in different events. To address this problem, we construct a head–tail event semantic constraint predicate framework that relates the complex semantics between different event components. However, considering the large-scale data, an automated method for generating constraint predicates is essential. Therefore, we combine parameter-efficient fine-tuning (PEFT) of large language models (LLMs) with retrieval-augmented generation (RAG) technologies. Specifically, this paper makes four significant contributions. Firstly, we construct a detailed framework of head–tail events semantic constraint predicates by combining manual definitions with the GPT-4o model. The framework includes 117 types of constraint predicates between head–tail events. Secondly, based on this framework, we annotate a dataset of head–tail events semantic constraint predicates and apply it to PEFT LLMs. Thirdly, we use PEFT LLMs prediction error data to construct an event knowledge base covering event entities, semantic roles, and entity types. Fourth, using the event knowledge base, the PEFT LLMs integrate the dual RAG techniques of keywords and vectors to improve the accuracy of generating the constraint predicates. Experimental results show that the method outperforms the baselines, achieving a precision of 97.18% and recall of 97.39%. This research fills the gap in semantic relationships between components across events and provides a novel approach for complex semantic generation tasks. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

A Fractional-Order Logarithmic Adaptive Filtering Algorithm Under α-Stable Noise 6

A Fractional-Order Logarithmic Adaptive Filtering Algorithm ...

引用

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Sun, Dazhi Yu, Canping Li, Li Li, Yingsong Xiao, Wudang Chen, Yong Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Aircraft Airworthiness Institute China Academy of Civil Aviation Science and Technology Center of Aviation Safety Technology Cast Beijing101399 China

ISBN: (纸本)9798350399059

In practical applications, noise is more appropriately modelled as an a-stable random process than as a Gaussian process. To cope with a-stable noise, a fractional-order stochastic gradient descent (SGD) method is invented to adaptive filtering (AF) algorithms. When both input signal and noise follow α-stable random processes, the AF algorithms based on mean square error (MSE) criteria can be affected. Nevertheless, the fractional-order AF (FoAF) algorithm can effectively address this issue. For the purpose of better stability performance of the FoAF algorithm, different cost functions (CFs) are introduced into fractional-order SGD method. Based on the fractional-order derivative of a logarithmic CF (LCF), a fractional-order logarithmic adaptive filtering (FoLAF) algorithm is formed in this condition. Trials show that the FoLAF algorithm achieves faster convergence, excellent steady-state performance and superior tracking performance. © 2023 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

2023 7th International Conference on Communication and Information Systems An Improved IOTA Protocol Based on Optimal Midway Walk 7

2023 7th International Conference on Communication and Infor...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Wu, Hongcheng Zhi, Hui Liu, Yangyang Anhui University School of Electronic and Information Engineering Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230601 China Hefei Zhilian Technology Industry Investment Co. Ltd Hefei230601 China

ISBN: (纸本)9798350330540

IOTA (Internet of Things Applications) protocol aims to provide a secure and trustworthy protocol for realizing data-value interactions between IoT devices, and it has become the next possible direction for the development of Blockchain applications. IOTA protocol has the problem that the time-consuming cumulative weight update grows too fast with the increase of the number of transactions, this paper proposed an improved IOTA protocol based on optimal midway walk, the improved protocol uses cutting-edge transaction selection algorithm of weighted Monte Carlo Markov random walk to reduce cumulative weight update delay. Firstly, this improved IOTA protocol mainly ensures the efficiency of transaction confirmation without losing the security of consensus by introducing the optimal midway walk method, i.e., the starting point of each walk is chosen to depart at an optimal location. Secondly, this paper designs the indirect verification identity record algorithm and the layer degree of confirmation principle are designed to realize the improved IOTA protocol's resilience and resistance to Parasite chain attack. The experimental results show that the improved IOTA using random function to select the midway walk starting point from i-50λ, to i-75λsubstantially solves the system computational burden problem and greatly reduces the cumulative weight update delay. © 2023 IEEE.

关键词： cumulative weight IOTA midway walk Parasite chain attack

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：