检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Youchao Huang, Heyan Wu, Zhijing School of Computer Science and Technology Beijing Institute of Technology Southeast Academy of Information Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention. Unlike generic retrieval queries, legal case queries are typically long and the definition of relevance is closely related to legal-specific elements. Therefore, legal case queries may suffer from noise and sparsity of salient content, which hinders retrieval models from perceiving correct information in a query. While previous studies have paid attention to improving retrieval models and understanding relevance judgments, we focus on enhancing legal case retrieval by utilizing the salient content in legal case queries. We first annotate the salient content in queries manually and investigate how sparse and dense retrieval models attend to those content. Then we experiment with various query content selection methods utilizing large language models (LLMs) to extract or summarize salient content and incorporate it into the retrieval models. Experimental results show that reformulating long queries using LLMs improves the performance of both sparse and dense models in legal case retrieval. © 2023, CC BY-NC-SA.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Multi-Attribute Consistency Driven Visual Language Framework for Surface Defect Detection

Multi-Attribute Consistency Driven Visual Language Framework...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Bin Kang Bin Chen Junjie Wang Weizhi Xian Huifeng Chang Chengdu Institute of Computer Applications University of Chinese Academy of Sciences Beijing China International Research Institute for Artificial Intelligence Harbin Institute of Technology(Shenzhen) Shenzhen China School of Computer Science and Technology Harbin Institute of Technology(Shenzhen) Shenzhen China Chongqing Research Institute Harbin Institute of Technology Chongqing China Co. Ltd CECloud Computing Technology Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Visual Language Pre-training models encounter significant challenges stemming from the scarcity of data and the presence of ambiguous cues in industrial defect detection tasks. In this work, we propose a multi-attribute consistency-driven defect detection (MACD) framework to optimize text prompts in a coarse-to-fine trajectory. To bridge differences in domain knowledge, we build a structured attribute repository that contains descriptions of various defects’ inherent attributes. Based on this, we propose a multi-attribute consistency (MAC) module that can adequately model the global alignment between sentences with multiple attributes and defect images. Furthermore, we design a refined cross-alignment (RCA) module to determine the fine-grained correspondence between each attribute and the region within the image. Finally, the proposed method is experimentally validated on two benchmarks, resulting in significant performance improvements in a wide range of defective scenarios.

关键词： Bridges Visualization Inspection Benchmark testing Data models Trajectory Defect detection

来源：评论

学校读者我要写书评

暂无评论

Method for constructing multi-dimensional feature map of malicious code 5

Method for constructing multi-dimensional feature map of mal...

引用

2020 5th International Seminar on computer technology, Mechanical and Electrical Engineering, ISCME 2020

作者： Ma, Haocong Zhang, Ji Zhou, Junhua Zhai, Xiang Xue, Junjie Ji, Hang State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing100854 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing100854 China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing100854 China

Malicious code is characterized by a large number of types, rapid increase in number, continuous update of transmission routes, and continuous enhancement of back analysis and back detection methods. Therefore, how to effectively detect and analyze malicious code has been a problem of great concern. This paper studies the features of binary file and disassembly file of malicious code, introduces the concept of information gain, and proposes a method to construct the multi-dimensional characteristic graph of malicious code. Finally, the convolutional neural network is used to classify the multi-dimensional feature graph of malicious code, which provides a new idea for the feature extraction of malicious code. © Published under licence by IOP Publishing Ltd.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multi-Source Domains Adaptation with Locally Topological Persevering

Unsupervised Multi-Source Domains Adaptation with Locally To...

引用

Chinese Automation Congress (CAC)

作者： Zhifeng Chen Lvda Wang Ying Li Shihui Ying Department of Mathematics College of Science Shanghai University Beijing Institute of Computer Technology and Applications College of Computer Engineering and Science Shanghai University

Most existing unsupervised domain adaptation (UDA) methods primarily focus on single-source and single-target domain scenarios, referred to as single-source unsupervised domain adaptation. However, in practical applications, it is often possible to collect labeled data from multiple distinct source domains, which not only differ from the target domain but also exhibit dissimilarities among themselves. As a result, the concept of multi-source unsupervised domain adaptation has emerged. While mainstream UDA techniques aim to align features between two domains, addressing domain shift solely through feature alignment might prove inadequate, potentially undermining the inherent structure of the data. To mitigate this risk, this paper introduces a method called Locally Topology Preserving Multi-Source Unsupervised Domain Adaptation (LTP- MDA). By performing clustering on both source and target data, distinct clusters are formed. During the domain-adaptive feature transformation, this method ensures the preservation of the structural integrity of these clusters throughout the transformation. Additionally, due to the possibility of misclassification during the clustering process, we leverage consistency weights derived from genuine labels in the source domain and pseudo-labels in the target domain to guide the clustering process. Experimental results demonstrate the remarkable performance of our approach across various cross-domain adaptation tasks. We extensively evaluate our method on three benchmark datasets, validating its effectiveness and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain applications

arXiv

引用

arXiv 2023年

作者： Yang, Yizhe Sun, Huashan Li, Jiawei Liu, Runheng Li, Yinghao Liu, Yuhang Gao, Yang Huang, Heyan School of Computer Science Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Southeast Academy of Information Technology China

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by developing increasingly large-scale models, there could be another branch to develop lightweight custom models that better serve certain domains, taking into account the high cost of training and deploying LLMs and the scarcity of resources. In this paper, we present MindLLM, a novel series of bilingual lightweight large language models, trained from scratch, alleviating such burdens by offering models with 1.3 billion and 3 billion parameters. A thorough account of experiences accrued during large model development is given, covering every step of the process, including data construction, model architecture, evaluation, and applications. Such insights are hopefully valuable for fellow academics and developers. MindLLM consistently matches or surpasses the performance of other open-source larger models on some public benchmarks. We also introduce an innovative instruction tuning framework tailored for smaller models to enhance their capabilities efficiently. Moreover, we explore the application of MindLLM in specific vertical domains such as law and finance, underscoring the agility and adaptability of our lightweight models. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

MD-TransUNet: TransUNet with Multi-attention and Dilated Convolution for Brain Stroke Lesion Segmentation 19th

MD-TransUNet: TransUNet with Multi-attention and Dilated C...

引用

19th EAI International Conference on Collaborative Computing: Networking, applications and Worksharing, CollaborateCom 2023

作者： Xu, Jie Wan, Jian Zhang, Xin School of Computer Science and Technology Hangzhou Dianzi University Zhejiang310018 China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Ministry of Education Beijing China School of Information and Electronic Engineering Zhejiang University of Science and Technology Zhejiang China Key Laboratory of Marine Ecosystem Dynamics Second Institute of Oceanography Ministry of Natural Resources Hangzhou China

ISBN: (纸本)9783031545276

The accurate segmentation of stroke lesion regions holds immense significance in shaping treatment strategies and rehabilitation protocols. Due to the large difference in the volume of stroke lesion areas and the great similarity between lesion areas and normal tissues, most of the existing methods for lesion segmentation cannot deal with these problems well. This paper proposes a novel network named MD-TransUNet for the segmentation of stroke lesions, whose framework is based on the UNet architecture. To fully obtain deep image features, it uses ResNet50 for downsampling. MD (multi-dilated) module is employed as the skip connection to gain more receptive fields. Different receptive fields can adapt to varying volumes of lesion areas. Then, a feature extraction module with multi-level attention mechanism is designed using ConvLSTM, non-local spatial attention, and channel attention modules to suppress useless information expression in skip connections and upsampling processes while focusing more on effective spatial and channel information in features. The experiments show that our proposed network gets superior performance than benchmark methods and indicates the generalization and effectiveness of the proposed model. © ICST institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer

arXiv

引用

arXiv 2023年

作者： Sun, Huashan Wu, Yixiao Ye, Yuhao Yang, Yizhe Li, Yinghao Li, Jiawei Gao, Yang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

SciMRC: Multi-perspective Scientific Machine Reading Comprehension

arXiv

引用

arXiv 2023年

作者： Zhang, Xiao Zheng, Heqi Nie, Yuxiang Huang, Heyan Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China

Scientific machine reading comprehension (SMRC) aims to understand scientific texts through interactions with humans by given questions. As far as we know, there is only one dataset focused on exploring full-text scientific machine reading comprehension. However, the dataset has ignored the fact that different readers may have different levels of understanding of the text, and only includes single-perspective question-answer pairs, leading to a lack of consideration of different perspectives. To tackle the above problem, we propose a novel multi-perspective SMRC dataset, called SciMRC, which includes perspectives from beginners, students and experts. Our proposed SciMRC is constructed from 741 scientific papers and 6,057 question-answer pairs. Each perspective of beginners, students and experts contains 3,306, 1,800 and 951 QA pairs, respectively. The extensive experiments on SciMRC by utilizing pre-trained models suggest the importance of considering perspectives of SMRC, and demonstrate its challenging nature for machine comprehension. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Regret with Unknown Delays

SSRN

引用

SSRN 2023年

作者： Wu, Ping Liu, Zhengyang Lu, Haolin Huang, Heyan School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

We study the problem of online convex optimization in dynamic environments with unknown and arbitrary delays. Without delays, existing work has achieved the optimal $\Theta(\sqrt{(1+\Delta_T)T})$ regret bound for any given sequence of comparators, where $T$ is the time horizon and $\Delta_T$ is the path-length of the comparator sequence. However, their algorithm assumes that the loss function can be revealed immediately to the agent after making the decision. In this paper, we propose a novel algorithm to tackle the delayed setting. We show that it enjoys $\mathcal{O}(\max\{\sqrt{(1+\Delta_T)D_T},(\hat{d}-1)\Delta_T\})$ regret bound, where $\hat{d}$ is the maximum delay and $D_T$ is the cumulative delay over the whole horizon. To complement our algorithm, we also establish an $\Omega(\sqrt{(1+\Delta_T)D_T})$ lower bound. The basic idea is to employ a delayed meta algorithm to track parallel delayed expert algorithms with varying step sizes. We further extend our algorithm to the case that we have no idea about the time horizon and cumulative delay using a novel doubling trick. Finally, numerical simulations are provided to illustrate the validity of our theoretical results. © 2023, The Authors. All rights reserved.

关键词： Comparators (optical)

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：