检索结果-内蒙古大学图书馆

Discriminative Word Alignment Over Multiple Word Segmentations

Chinese Journal of Electronics 2025年第2期23卷 263-270页

作者： Ning Xi Xinyu Dai Shujian Huang Jiajun Chen Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Conventional bilingual word alignment is conducted on sentence pairs with single word segmentation for languages such as Chinese, viz. Single-segmentation-based word alignment (SSWA). However, SSWA may run the risk of losing optimal word segmentation granularities or causing data sparseness in word alignment. This paper proposes Multiple-segmentation-based word alignment (MSWA). In MSWA, diverse and complementary knowledge in multiple word segmentations can be employed to lower the above risks in word alignment. Given $k$ word segmentations of a Chinese sentence, a skeleton segmentation is firstly constructed. The alignment between the skele-ton segmentation and the parallel English sentence is log-linearly modeled, where various features defined over multiple word segmentations are incorporated. The Viterbi alignment, the alignment with the highest score, is mapped back to $k$ word alignments based on $k$ segmentations respectively. Experimentally, MSWA outperformed SSWA on all $k$ segmentations in both alignment quality and translation performance.

关键词： Translation Viterbi algorithm Social sciences Education Medical services Skeleton

来源：评论

学校读者我要写书评

暂无评论

Quantum Pseudorandom Scramblers 22nd

Quantum Pseudorandom Scramblers

引用

22nd Theory of Cryptography Conference, TCC 2024

作者： Lu, Chuhan Qin, Minglong Song, Fang Yao, Penghui Zhao, Mingnan Computer Science Department Portland State University Portland United States State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Hefei National Laboratory Hefei230088 China

ISBN: (纸本)9783031780165

Quantum pseudorandom state generators (PRSGs) have stimulated exciting developments in recent years. A PRSG, on a fixed initial (e.g., all-zero) state, produces an output state that is computationally indistinguishable from a Haar random state. However, pseudorandomness of the output state is not guaranteed on other initial states. In fact, known PRSG constructions provably fail on some initial states. In this work, we propose and construct quantum Pseudorandom state Scramblers (PRSSs), which can produce a pseudorandom state on an arbitrary initial state. In the information-theoretical setting, we obtain a scrambler which maps an arbitrary initial state to a distribution of quantum states that is close to Haar random in total variation distance. As a result, our scrambler exhibits a dispersing property. Loosely, it can span an ϵ-net of the state space. This significantly strengthens what standard PRSGs can induce, as they may only concentrate on a small region of the state space provided that the average output state approximates a Haar random state. Our PRSS construction develops a parallel extension of the famous Kac’s walk, and we show that it mixes exponentially faster than the standard Kac’s walk. This constitutes the core of our proof. We also describe a few applications of PRSSs. While our PRSS construction assumes a post-quantum one-way function, PRSSs are potentially a weaker primitive and can be separated from one-way functions in a relativized world similar to standard PRSGs. © International Association for Cryptologic Research 2025.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Local Community Detection in Multi-Attributed Road-Social Networks

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3514-3527页

作者： Ni, Li Li, Qiuyu Zhang, Yiwen Luo, Wenjian Sheng, Victor S. Anhui University School of Computer Science and Technology Hefei Anhui230601 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China Texas Tech University School of Department of Computer Science United States

The information available in multi-attributed road-social networks includes network structure, location information, and numerical attributes. Most studies mainly focus on mining communities by combining structure with attributes or structure with location, which do not consider structure, attributes, and location simultaneously. Therefore, we propose a parameter-free algorithm, called LCDMRS, to mine local communities in multi-attributed road-social networks. LCDMRS extracts a sub-network surrounding the given node and embeds it to generate the vector representations of nodes, which incorporates both structural and attributed information. Based on the vector representations of nodes, the average cosine similarity between nodes is designed to ensure both the structural and attributed cohesiveness of the community, while the community node density is designed to ensure the spatial cohesiveness of the community. Targeting the community node density and cosine similarity of nodes, LCDMRS takes the given node as the starting node and employs the community dominance relation to expand the community outward. Experimental results on multiple real-world datasets demonstrate LCDMRS outperforms comparison algorithms. © 1989-2012 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Feature Alignment via Knowledge Distillation 21st

Personalized Federated Learning with Feature Alignment via...

引用

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

作者： Qi, Guangfei Qu, Zhihao Lyu, Shen-Huan Jia, Ninghui Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9789819601189

Personalized Federated Learning (PFL) has gained significant attention for its ability to handle heterogeneous data effectively. Parameter decoupling is a typical approach to PFL. It decouples the model into a feature extractor and a classifier head, where the feature extractor is trained collaboratively to learn a common representation and the classifier head is personalized for local data. Since local training only learns personalized feature information and ignores global information, the generalization ability of the feature extractor is limited. To improve the performance of the local model, a feasible approach is to make the local feature extractor more generalized. However, prior work requires the transmission of additional feature data beyond the transmission of model parameters, which leads to privacy leakage and higher communication overhead. To address these shortcomings, we propose a PFL algorithm with feature alignment via knowledge distillation, named PFAKD. PFAKD enhances the training of local feature extractors by explicitly aligning each sample’s local features with global features, providing more detailed guidance. Meanwhile, it avoids additional communication overhead and the risk of privacy leakage. We conduct extensive experiments in heterogeneous data scenarios. PFAKD outperforms other state-of-the-art methods by up to 4.35% in terms of model accuracy. Our code is available at https://***/fei0829/PFAKD. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Tu, Longchuan Meng, Shunmei Liu, Xiao Liu, Guanfeng Beheshti, Amin Zhang, Xuyun School of Computer Science and Engineering Nanjing University of Science and Technology Nanjin China State Key Laboratory for Novel Software Technology Nanjing University Nanjin China School of Computing Macquarie University Sydney Australia

ISBN: (纸本)9789819605699

Recently, graph neural networks(GNNs) have played a key crucial in many recommendation situations. In particular, contrastive learning-based hypergraph neural networks (HGNNs) are gradually becoming a research focus for addressing issues of data sparsity and noise. Despite many studies proving their outstanding performance, there are still some shortcomings: i) Most contrastive learning-based HGNNs primarily rely on cross-view contrastive learning, while neglecting contrastive learning on the interaction graph. ii) Utilizing node embedding for hypergraph structure learning is susceptible to the influence of low-quality representations, thereby constraining the learning capability of HGNNs. To address these issues, we offer a Semantic Similarity-based Graph Contrastive Learning framework (SSGCL), which aims to jointly learn representations with rich semantic information through within-view and cross-view contrastive learning. Specifically, we first introduce consistency contrastive learning, which captures self-supervised signals through semantic similarity between nodes and their neighborhoods. It better captures the unique features of nodes through the connections between nodes and their neighborhoods. Then, we utilize interaction graph learning hypergraph structure, promoting it to extract potential node connections and thus improving its ability to describe homogeneous node relationships. Experimental evaluations on three actual datasets show that SSGCL performs much better than the current baseline models. © 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

Momentum Posterior Regularization for Multi-hop Dense Retrieval 31

Momentum Posterior Regularization for Multi-hop Dense Retrie...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xia, Zehua Wu, Yuyang Xia, Yiyun Nguyen, Cam-Tu State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science Nanjing University China School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798891761964

Multi-hop question answering (QA) often requires sequential retrieval (multi-hop retrieval), where each hop retrieves missing knowledge based on information from previous hops. To facilitate more effective retrieval, we aim to distill knowledge from a posterior retrieval, which has access to posterior information like an answer, into a prior retrieval used during inference when such information is unavailable. Unfortunately, current methods for knowledge distillation in one-time retrieval are ineffective for multi-hop QA due to two issues: 1) Posterior information is often defined as the response (i.e. the answer), which may not clearly connect to the query without intermediate retrieval;and 2) The large knowledge gap between prior and posterior retrievals makes existing distillation methods unstable, even resulting in performance loss. As such, we propose MoPo (Momentum Posterior Regularization) with two key innovations: 1) Posterior information of one hop is defined as a query-focus summary from the golden knowledge of the previous and current hops;2) We develop an effective training strategy where the posterior retrieval is updated along with the prior retrieval via momentum moving average method, allowing smoother and effective distillation. Experiments on HotpotQA and StrategyQA demonstrate that MoPo outperforms existing baselines in both retrieval and downstream QA tasks. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

MG+: Towards Efficient Context Inconsistency Detection by Minimized Link Generation

MG+: Towards Efficient Context Inconsistency Detection by Mi...

引用

作者： Chen, Chuyang Wang, Huiyan Zhang, Lingyu Xu, Chang Yu, Ping State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China School of Computer Science Nanjing University Jiangsu Nanjing China Software Institute Nanjing University Jiangsu Nanjing China

Self-adaptive applications are becoming increasingly attractive, with the ability to smartly understand their runtime environments (or contexts) and deliver adaptive services, for example, location-aware navigation or resource-sensitive suggestions. However, due to inherent noises in the process of sensing and interpreting environmental information, there is a growing demand for guarding the consistency of collected contexts to avoid application misbehaviour and, at the same time, minimize extra costs. Existing work attempted to achieve this by speeding up the kernel constraint checking module inside the consistency guarding process. Most of these efforts were spent on reusing previous checking results or parallelizing the checking process, but they all leave one central step of constraint checking, that is, link generation, untouched. In this step, the checking engine provides reasons to explain the violation of constraints under check. It occupies a substantial part of the total time cost. Focusing on this key link generation step, we proposed MG, which deploys a rigourous analysis to automatically identify and avoid redundancy in the link generation without harming any correctness of the checking results. MG has been proven sound (always guaranteeing correctness) and complete (entirely removing redundancy). Moreover, based on our observation that MG's redundancy elimination also assists another core step of constraint checking to reduce unnecessary computation further, we additionally enhance MG with an escape-condition optimization to escape unnecessary evaluation of truth values to further improve the efficiency of constraint checking in an aspect other than link generation. We call it MG+ for distinguishing. Our experiments with synthesized and real-world consistency constraints reported that, compared with existing work, MG eliminates all link redundancy (83% to 0%), and based on it, MG+ further reduces significant truth value calculations (e.g., 49.74% reduc

关键词： constraint checking context inconsistency link redundancy

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Centered Dual-Process Reasoning for Math Word Problems with Large Language Models

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3457-3471页

作者： Liu, Jiayu Huang, Zhenya Liu, Qi Ma, Zhiyuan Zhai, Chengxiang Chen, Enhong University of Science and Technology of China School of Data Science China University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Anhui Hefei230000 China University of Science and Technology of China School of Computer Science and Technology China University of Illinois at Urbana-Champaign Department of Computer Science ChampaignIL61820 United States

Math word problem (MWP) serves as a critical milestone for assessing the text mining ability and knowledge mastery level of models. Recent advancements have witnessed large language models (LLMs) showcasing remarkable performance on MWP. However, current LLMs still frequently exhibit logical errors, which highlights their inability to fully grasp the knowledge required for genuine step-by-step mathematical reasoning. To this end, in this paper, we propose a novel Knowledgeguided Solver (KNOS) framework that empowers LLMs to simulate human mathematical reasoning, whose core idea is to Invoke-VerifyInject necessary knowledge to solve MWP. We draw inspiration from the dual-process theory to construct two cooperative systems: a Knowledge System and an Inference System. Specifically, the Knowledge System employs LLMs as the knowledge base and develops a novel knowledge invoker that can elicit their relevant knowledge to support the strict steplevel mathematical reasoning. In the Inference System, we propose a knowledge verifier and a knowledge injector to evaluate the knowledge rationality and further guide the step-wise symbolic deduction in an interpretable manner based on human cognitive mechanism, respectively. Moreover, to tackle the potential scarcity issue of mathematics-specific knowledge in LLMs, we consider an open-book exam scenario and propose an improved version of KNOS called EKNOS. In EKNOS, we meticulously design knowledge selectors to extract the most relevant commonsense and math formulas from external knowledge sources for each reasoning step. This knowledge is utilized to assist the knowledge invoker in better stimulating LLMs' reasoning abilities. Both KNOS and EKNOS are flexible to empower different LLMs. Our experiments with GPT3, ChatGPT, and GPT4 not only demonstrate their reasoning accuracy improvement but also show how they bring the strict step-wise interpretability of mathematical thinking. © 1989-2012 IEEE.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Research on Microkernel Integrity Semantics Model and Formal Verification

引用

Chinese Journal of Electronics 2025年第1期23卷 43-48页

作者： Zhenjiang Qian Wei Liu Hao Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

Microkernel integrity is an important aspect of security for the whole microkernel system. Many of the research works on microkernel integrity focus on analysis and safeguards against the existing kernel attacks, and security enhancements for the vulnerabilities of system design and implementation aspects. The formal methods for operating system design and verification ensure the system's high level of security. The existing formalization work and research for operating system mainly focus on the code-level verification of program correctness. In this paper, we propose a formal abstraction model of microkernel in order to accurately describe the semantics of every kernel behavior, and achieve the description of the whole kernel. Based on the model we illustrate the microkernel integrity criterions and elaborate on the integrity mechanism. Meanwhile, we formally verify the completeness and consistency between the mechanism and the definition of the microkernel integrity. We use the self-implemented operating system VTOS (Verified trusted operating system) as an example to illustrate the design method for the microkernel integrity.

关键词： Design methodology Semantics Security Personnel Logic Kernel Protection System analysis and design Research and development Formal verification

来源：评论

学校读者我要写书评

暂无评论

Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion 23rd

Finetuning Generative Large Language Models with Discrimina...

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Liu, Yang Tian, Xiaobin Sun, Zequn Hu, Wei State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China National Institute of Healthcare Data Science Nanjing University Nanjing210093 China

ISBN: (纸本)9783031778438

Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG entities, which inevitably brings errors. In this paper, we present a finetuning framework, DIFT, aiming to unleash the KG completion ability of LLMs and avoid grounding errors. Given an incomplete fact, DIFT employs a lightweight model to obtain candidate entities and finetunes an LLM with discrimination instructions to select the correct one from the given candidates. To improve performance while reducing instruction data, DIFT uses a truncated sampling method to select useful facts for finetuning and injects KG embeddings into the LLM. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed framework. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

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：