检索结果-内蒙古大学图书馆

Entity concept-enhanced few-shot relation extraction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Shan Zhang, Yongfei Niu, Guanglin Zhao, Qinhua Pu, Shiliang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering BeiHang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing100191 China Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering BeiHang University Beijing100191 China Hikvision Research Institute Hangzhou311500 China

Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized entity pairs, due to limited samples and lack of knowledge. To address this problem, in this paper, we proposed a novel entity CONCEPTenhanced FEw-shot Relation Extraction scheme (ConceptFERE), which introduces the inherent concepts of entities to provide clues for relation prediction and boost the relations classification performance. Firstly, a conceptsentence attention module is developed to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. Secondly, a self-attention based fusion module is presented to bridge the gap of concept embedding and sentence embedding from different semantic spaces. Extensive experiments on the FSRE benchmark dataset FewRel have demonstrated the effectiveness and the superiority of the proposed ConceptFERE scheme as compared to the state-of-the-art baselines. Code is available at https://***/LittleGuoKe/ConceptFERE. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

A novel Skin lesion prediction and classification technique: ViT-GradCAM

学校读者我要写书评

暂无评论

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI) 2024年第9期30卷 e70040页

作者： Muhammad Shafiq Kapil Aggarwal Jagannathan Jayachandran Gayathri Srinivasan Rajasekhar Boddu Adugna Alemayehu School of Information Engineering Qujing Normal University Qujing China. Key Laboratory of Intelligent Sensor and System Design College of Information Engineering Qujing Normal University Qujing China. Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India. Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Katpadi Vellore India. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India. Department of AIML Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Hyderabad India. Lecturer in Software Engineering Wachemo University Hosaina Ethiopia.

BACKGROUND:Skin cancer is one of the highly occurring diseases in human life. Early detection and treatment are the prime and necessary points to reduce the malignancy of infections. Deep learning techniques are supplementary tools to assist clinical experts in detecting and localizing skin lesions. Vision transformers (ViT) based on image segmentation classification using multiple classes provide fairly accurate detection and are gaining more popularity due to legitimate multiclass prediction capabilities. MATERIALS AND METHODS:In this research, we propose a new ViT Gradient-Weighted Class Activation Mapping (GradCAM) based architecture named ViT-GradCAM for detecting and classifying skin lesions by spreading ratio on the lesion's surface area. The proposed system is trained and validated using a HAM 10000 dataset by studying seven skin lesions. The database comprises 10 015 dermatoscopic images of varied sizes. The data preprocessing and data augmentation techniques are applied to overcome the class imbalance issues and improve the model's performance. RESULT:The proposed algorithm is based on ViT models that classify the dermatoscopic images into seven classes with an accuracy of 97.28%, precision of 98.51, recall of 95.2%, and an F1 score of 94.6, respectively. The proposed ViT-GradCAM obtains better and more accurate detection and classification than other state-of-the-art deep learning-based skin lesion detection models. The architecture of ViT-GradCAM is extensively visualized to highlight the actual pixels in essential regions associated with skin-specific pathologies. CONCLUSION:This research proposes an alternate solution to overcome the challenges of detecting and classifying skin lesions using ViTs and GradCAM, which play a significant role in detecting and classifying skin lesions accurately rather than relying solely on deep learning models.

关键词： Grad‐CAM Multi‐Headed Self attention (MSA) linear patch projection multilayer perceptron (MLP) skin lesion transformer encoder vision transformer (ViT)

Vulnerability Analysis through Interface-based Checker Design

学校读者我要写书评

暂无评论

Vulnerability Analysis through Interface-based Checker Desig...

IEEE International Conference on software quality, Reliability and Security Companion (QRS-C)

作者： Xiang Du Liangze Yin Peng Wu Liyuan Jia Wei Dong Key Laboratory Of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha China

ISBN: (数字)9781728189154

ISBN: (纸本)9781728189161

Checkers design is a main step for static analysis of different vulnerabilities. This paper focuses on static analysis on code property graph, which combines abstract syntax tree, control flow graph, and program dependence graph. Developing checkers on code property graph directly is usually complex and difficult. In this paper, we have analyzed a large number of checkers of different vulnerabilities, and extracted those most commonly used operations as a set of interfaces. We have implemented these interfaces and developed a set of vulnerability checkers based on them. The practical efficacy of these checkers are evaluated on the Linux kernel source code. Experimental results show that our proposed interfaces are strong enough to express most vulnerabilities and our implementation is effective for vulnerabilities detection.

关键词： Linux software algorithms Static analysis software quality Syntactics software reliability Kernel

Graph-based Vulnerability Detection via Extracting Features from Sliced Code

学校读者我要写书评

暂无评论

Graph-based Vulnerability Detection via Extracting Features ...

IEEE International Conference on software quality, Reliability and Security Companion (QRS-C)

作者： Peng Wu Liangze Yin Xiang Du Liyuan Jia Wei Dong Key Laboratory Of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha China

ISBN: (数字)9781728189154

ISBN: (纸本)9781728189161

With the development of open source software and open source community, there are more available codes on the Internet. And the open vulnerability information can be found on the Internet. In fact, using known vulnerabilities to calculate the similarity with the source code has been demonstrated a useful method to detect vulnerabilities. But the vulnerabilities often have many irrelevant codes, which may cause false positives and reduce the accuracy of vulnerability detection. Besides, the program code may have been patched. This also leads to false positives. We use code property graphs to extract source code and calculate the similarity between the vulnerable code and the source code to judge whether the software has vulnerabilities. By using the patched code, we can reduce the false positive. We use our approach on LibTIFF and Linux kernel. The experimental results show that the approach can effectively find vulnerabilities and reduce the false positive.

关键词： Linux software quality Feature extraction Internet software reliability Security Open source software

Gathering github oss requirements from q&a community: An empirical study

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Huang, Hao Lu, Yao Mao, Xinjun Key Laboratory of Software Engineering for Complex Systems College of Computer National University of Defense Technology Changsha410073 China

ross-community collaboration can exploit the expertise and knowledges of crowds in different communities. Recently increasing users in open source software (OSS) community like GitHub attempt to gather software requirements from question and answer (Q&A) communities such as Stack Overflow (SO). In order to investigate this emerging cross-community collaboration phenomenon, the paper presents an exploratory study on cross-community requirements gathering of OSS projects in GitHub. We manually sample 3266 practice cases and quantitatively analyze the popularity of the phenomenon, the characteristics of the gathered requirements, and collaboration behaviors of cross-community. Some important findings are obtained: more than half of the requirements gathered from SO are enhancements and the majority of the gathered requirements are non-functional requirements. In addition, OSS developers can directly obtain related solutions and contributions of the gathered requirements from SO in the gathering process. Copyright © 2020, The Authors. All rights reserved.

关键词： Requirements engineering

A Generalized Binary Tree Mechanism for Differentially Private Approximation of All-Pair Distances

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dinitz, Michael Fan, Chenglin Liu, Jingcheng Upadhyay, Jalaj Zou, Zongrui Department of Computer Science Johns Hopkins University United States Department of Computer Science and Engineering Seoul National University Korea Republic of State Key Laboratory for Novel Software Technology New Cornerstone Science Laboratory Nanjing University China Management Science & Information Systems Department Rutgers University United States

We study the problem of approximating all-pair distances in a weighted undirected graph with differential privacy, introduced by Sealfon [Sea16]. Given a publicly known undirected graph, we treat the weights of edges as sensitive information, and two graphs are neighbors if their edge weights differ in one edge by at most one. We obtain efficient algorithms with significantly improved bounds on a broad class of graphs which we refer to as recursively separable. In particular, for any n-vertex Kh-minor-free graph, our algorithm achieve an additive error of Õ(h(nW)1/3), where W represents the maximum edge weight;For grid graphs, the same algorithmic scheme achieve additive error of Õ(n1/4√W). Our approach can be seen as a generalization of the celebrated binary tree mechanism for range queries, as releasing range queries is equivalent to computing all-pair distances on a path graph. In essence, our approach is based on generalizing the binary tree mechanism to graphs that are recursively separable. Copyright © 2025, The Authors. All rights reserved.

关键词： Binary trees

Towards the hierarchical state machine oriented proteus systems programming language

学校读者我要写书评

暂无评论

Towards the hierarchical state machine oriented proteus syst...

Accelerating Space Commerce, Exploration, and New Discovery Conference, ASCEND 2020

作者： Tellier, Daniel Millman, Meyer McClelland, Brian Go, Kate Beatrix Balayan, Alice Munje, Michael J. Dewey, Kyle Ho, Nhut Havelund, Klaus Ingham, Michel Department of Computer Science California State University Northridge NorthridgeCA91330 United States Department of Electrical and Computer Engineering California State University Northridge NorthridgeCA91330 United States Department of Mechanical Engineering California State University Northridge NorthridgeCA91330 United States Laboratory for Reliable Software Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States Systems Engineering Division Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States

ISBN: (纸本)9781624106088

In space applications, hierarchical state machines (HSMs) are often used for writing simulation and control software, including that of the Curiosity rover. At the Jet Propulsion Lab (JPL), multiple programming languages have been developed specifically for writing HSM-based software, and these have been used in practice. However, we observe that the existing languages developed have significant issues with one or more of usability, performance, and safety, making them problematic for HSM-based development. To address these concerns, we are taking lessons learned from these languages and developing a new programming language named Proteus. Proteus builds HSM support directly into the language, and permits complex HSMs to be defined which communicate with each other. Proteus is designed with a look and feel similar to C/C++, making it usable and overall approachable for use by JPL systems engineers. Proteus itself compiles to C++, allowing it to fit easily into existing development toolchains, and making it amenable to embedded real-time systems. To ensure that Proteus will be of use to its target audience, it is being developed iteratively through a series of prototypes which are regularly evaluated by key stakeholders at JPL, allowing us to refine its design if we go off course. While Proteus is still very young in its development, we demonstrate its basic viability on an example utilizing multiple independent HSMs communicating with each other, and relevant execution traces. In the future, we plan to apply Proteus to larger HSMs taken from real space applications, and many additional relevant features are planned. © 2020 The MITRE Corporation. All Rights Reserved.

关键词：

SMedBERT: A knowledge-enhanced pre-trained language model with structured semantics for medical text mining

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Taolin Cai, Zerui Wang, Chengyu Qiu, Minghui Yang, Bite He, Xiaofeng School of Software Engineering East China Normal University Alibaba Group Shanghai Key Laboratory of Trsustworthy Computing School of Computer Science and Technology East China Normal University Dxy Shanghai Research Institute for Intelligent Autonomous Systems

Recently, the performance of Pre-trained Language Models (PLMs) has been significantly improved by injecting knowledge facts to enhance their abilities of language understanding. For medical domains, the background knowledge sources are especially useful, due to the massive medical terms and their complicated relations are difficult to understand in text. In this work, we introduce SMedBERT, a medical PLM trained on large-scale medical corpora, incorporating deep structured semantics knowledge from neighbours of linked-entity. In SMedBERT, the mention-neighbour hybrid attention is proposed to learn heterogeneousentity information, which infuses the semantic representations of entity types into the homogeneous neighbouring entity structure. Apart from knowledge integration as external features, we propose to employ the neighbors of linked-entities in the knowledge graph as additional global contexts of text mentions, allowing themto communicate via shared neighbors, thus enrich their semantic representations. Experiments demonstrate that SMedBERT significantly outperforms strong baselines in various knowledge-intensive Chinese medical tasks. It also improves the performance of other tasks such as question answering, questionmatching and natural language inference. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge graph

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Bo Zhang, Bob Zhang, Chengyang Zhou, Minghao Huang, Weiliang Wang, Shihang Wang, Qing Li, Mengran Zhang, Yong Song, Qianqian PAMI Research Group Department of Computer and Information Science University of Macau Taipa China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida Florida United States Faculty of Applied Sciences Macao Polytechnic University Taipa China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Department of Cancer Biology Wake Forest School of Medicine Winston SalemNC United States

In the field of image-based drug discovery, capturing the phenotypic response of cells to various drug treatments and perturbations is a crucial step. This process involves transforming high-throughput cellular images into quantitative representations for downstream analysis. However, existing methods require computationally extensive and complex multi-step procedures, which can introduce inefficiencies, limit generalizability, and increase potential errors. To address these challenges, we present PhenoProfiler, an innovative model designed to efficiently and effectively extract morphological representations, enabling the elucidation of phenotypic changes induced by treatments. PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods. It also includes a multi-objective learning module to enhance robustness, accuracy, and generalization in morphological representation learning. PhenoProfiler is rigorously evaluated on large-scale publicly available datasets, including over 230,000 whole-slide multi-channel images in end-to-end scenarios and more than 8.42 million single-cell images in non-end-to-end settings. Across these benchmarks, PhenoProfiler consistently outperforms state-of-the-art methods by up to 20%, demonstrating substantial improvements in both accuracy and robustness. Furthermore, PhenoProfiler uses a tailored phenotype correction strategy to emphasize relative phenotypic changes under treatments, facilitating the detection of biologically meaningful signals. UMAP visualizations of treatment profiles demonstrate PhenoProfiler’s ability to effectively cluster treatments with similar biological annotations, thereby enhancing interpretability. These findings establish PhenoProfiler as a scalable, generalizable, and robust tool for phenotypic learning, offering transformative advancement

关键词： Benchmarking