检索结果-内蒙古大学图书馆

Neural Architecture Search via Multi-Hashing Embedding and Graph Tensor Networks for Multilingual Text Classification

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2024年第1期8卷 350-363页

作者： Yan, Xueming Huang, Han Jin, Yaochu Chen, Liang Liang, Zhanning Hao, Zhifeng Guangdong Univ Foreign Studies Sch Informat Sci & Technol Guangzhou 510515 Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510515 Peoples R China South China Univ Technol Key Laboratoryof Big Data & Intelligent Robot SCUT Minist Educ China Guangzhou 510515 Peoples R China Bielefeld Univ Fac Technol D-33619 Bielefeld Germany Shantou Univ Coll Sci Dept Math Shantou 515063 Peoples R China

Neural architecture search (NAS) has been demonstrated to be promising in deep learning for text classification. Most existing NAS algorithms, however, are proposed for single-language text classification. They may become ineffective when extended to multilingual text classification because the differences in the syntactic structure and contextual semantics of different languages increase the computational complexity of NAS search. To address the above issue, this article proposes a differential neural architecture search approach using multi-hashing embedding for multilingual text representation. A multi-hashing network capable of processing heterogeneous graph information is constructed so that cross-language syntactic and contextual semantic information can be effectively represented. In addition, a neural tensor network with multi-hashing embedding is adopted as a continuous encoder to estimate the probability for each candidate operation in the search space, and reparameterization-based gradient search is employed to efficiently search for network architectures for multilingual text representation. Our experimental results on two multilingual text classification datasets demonstrate that the proposed approach outperforms the state-of-the-art NAS methods for text classification in terms of both classification accuracy and computational efficiency.

关键词： Gradient-based method multi-hashing embedding multilingual text classification neural architecture search neural tensor network

来源：评论

学校读者我要写书评

暂无评论

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

arXiv

引用

arXiv 2025年

作者： Chen, Jiali Hei, Xusen Xue, Yuqi Wu, Zihan Xie, Jiayuan Cai, Yi Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China School of Software Engineering South China University of Technology China The Hong Kong Polytechnic University Hong Kong

Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children’s reading preferences (i.e., vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters’ personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children’s reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Superpixel attention guided network for accurate and real-time salient object detection

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第27期81卷 38921-38944页

作者： Zhou, Zhiheng Guo, Yongfan Huang, Junchu Dai, Ming Deng, Ming Yu, Qingjun South China Univ Technol Sch Elect & Informat Engn Guangzhou Peoples R China South China Univ Technol Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China Dalian Neusoft Univ Informat Sch Digital Arts & Design Dalian Peoples R China

Edge information has been proven to be effective for remedying the unclear boundaries of salient objects. Current salient object detection (SOD) methods usually utilize edge detection as an auxiliary task to introduce explicit edge information. However, edge detection is unable to provide the indispensable regional information for SOD, which may result in incomplete salient objects. To alleviate this risk, observing that superpixels hold the inherent property that contains both edge and regional information, we propose a superpixel attention guided network (SAGN) in this paper. Specifically, we first devise a novel supervised deep superpixel clustering (DSC) method to form the relation between superpixels and SOD. Based on the DSC, we build a superpixel attention module (SAM), which provides superpixel attention maps that can neatly separate different salient foreground and background regions, while preserving accurate boundaries of salient objects. Under the guidance of the SAM, a lightweight decoder with a simple but effective structure is able to yield high-quality salient objects with accurate and sharp boundaries. Hence, our model only contains less than 5 million parameters and achieves a real-time speed of around 40 FPS. Whilst offering a lightweight model and fast speed, our method still outperforms other 11 state-of-the-art approaches on six benchmark datasets.

关键词： Salient object detection Superpixel segmentation Deep clustering Image segmentation

来源：评论

学校读者我要写书评

暂无评论

CoNav: A Benchmark for Human-Centered Collaborative Navigation

arXiv

引用

arXiv 2024年

作者： Li, Changhao Sun, Xinyu Chen, Peihao Fan, Jugang Wang, Zixu Liu, Yanxia Zhu, Jinhui Gan, Chuang Tan, Mingkui South China University of Technology China Pazhou Laboratory China UMass Amherst United States MIT-IBM Watson AI Lab United States Key Laboratory of Big Data and Intelligent Robot Ministry of Education China

Human-robot collaboration, in which the robot intelligently assists the human with the upcoming task, is an appealing objective. To achieve this goal, the agent needs to be equipped with a fundamental collaborative navigation ability, where the agent should reason human intention by observing human activities and then navigate to the human's intended destination in advance of the human. However, this vital ability has not been well studied in previous literature. To fill this gap, we propose a collaborative navigation (CoNav) benchmark. Our CoNav tackles the critical challenge of constructing a 3D navigation environment with realistic and diverse human activities. To achieve this, we design a novel LLM-based humanoid animation generation framework, which is conditioned on both text descriptions and environmental context. The generated humanoid trajectory obeys the environmental context and can be easily integrated into popular simulators. We empirically find that the existing navigation methods struggle in CoNav task since they neglect the perception of human intention. To solve this problem, we propose an intentionaware agent for reasoning both long-term and short-term human intention. The agent predicts navigation action based on the predicted intention and panoramic observation. The emergent agent behavior including observing humans, avoiding human collision, and navigation reveals the efficiency of the proposed datasets and agents. Copyright © 2024, The Authors. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Nonreciprocity of energy transfer in a nonlinear asymmetric oscillator system with various vibration states

引用

Applied Mathematics and Mechanics(English Edition) 2023年第5期44卷 727-744页

作者： Jian’en CHEN Jianling LI Minghui YAO Jun LIU Jianhua ZHANG Min SUN Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin 300384China School of Aeronautics and Astronautics Tiangong UniversityTianjin 300387China Agricultural Information Institute of Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big DataMinistry of Agriculture and Rural AffairsBeijing 100081China School of Science Tianjin Chengjian UniversityTianjin 300384China

The nonreciprocity of energy transfer is constructed in a nonlinear asymmetric oscillator system that comprises two nonlinear oscillators with different parameters placed between two identical linear *** slow-flow equation of the system is derived by the complexification-averaging *** semi-analytical solutions to this equation are obtained by the least squares method,which are compared with the numerical solutions obtained by the Runge-Kutta *** distribution of the average energy in the system is studied under periodic and chaotic vibration states,and the energy transfer along two opposite directions is *** effect of the excitation amplitude on the nonreciprocity of the system producing the periodic responses is analyzed,where a three-stage energy transfer phenomenon is *** the first stage,the energy transfer along the two opposite directions is approximately equal,whereas in the second stage,the asymmetric energy transfer is *** energy transfer is also asymmetric in the third stage,but the direction is reversed compared with the second ***,the excitation amplitude for exciting the bifurcation also shows an asymmetric *** vibrations are generated around the resonant frequency,irrespective of which linear oscillator is *** excitation threshold of these chaotic vibrations is dependent on the linear oscillator that is being *** addition,the difference between the energy transfer in the two opposite directions is used to further analyze the nonreciprocity in the *** results show that the nonreciprocity significantly depends on the excitation frequency and the excitation amplitude.

关键词： nonreciprocity strong nonlinearity energy transfer chaotic vibration higher branch of response

来源：评论

学校读者我要写书评

暂无评论

Multimodal multiscale dynamic graph convolution networks for stock price prediction

引用

PATTERN RECOGNITION 2024年 149卷

作者： Liu, Ruirui Liu, Haoxian Huang, Huichou Song, Bo Wu, Qingyao Brunel Univ London Dept Econ & Finance London England Kings Coll London Data Analyt Finance & Macro Ctr London England South China Univ Technol Sch Software Engn Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China City Univ Hong Kong Coll Business Global Res Unit Hong Kong Peoples R China South China Univ Technol Guangzhou Higher Educ Mega Ctr 382 Zhonghuan Rd East Guangzhou 510006 Peoples R China

Predicting directional future stock price movements is very challenging due to the complex, stochastic, and evolving nature of the financial markets. Existing literature either neglects other timely and granular alternative data, such as media text data, or fails to extract and distill predictive multimodal features from the data. Moreover, the time -varying cross-sectional relations beyond sequential dependencies of stock prices are informative for forecasting price fluctuations, for which the modelling flexibility, however, is not adequate in most of the previous studies. In this paper, we propose a novel Multiscale Multimodal Dynamic Graph Convolution Network (Melody-GCN) to address these issues in stock price prediction. It contains three core modules: (1) multimodal fusing -diffusing blocks that effectively integrate and align the numerical and textual features;(2) a multiscale architecture that extracts and refines temporal features via a fine -to -coarse descending path and a coarse -to -fine ascending path progressively;and (3) dynamic spatio-temporal graph convolutional layers that learn the complex and evolving stock relations not only in between industries and individual companies but also across time horizons. Extensive experimental results and trading simulations on two realworld datasets demonstrate the superior performance of our proposed approach beyond other state-of-the-art models.

关键词： Stock movement prediction Multimodal feature fusing Multiscale architecture Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Image Matching Algorithm Under Adverse Conditions Based on SIFT

Image Matching Algorithm Under Adverse Conditions Based on S...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Hao Chen Xinrong Cao Zuoyong Li Lihui Lin College of Computer and Big Data Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Wuyi University Fujian China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Image matching technology is crucial in computer vision applications. However, the traditional SIFT (Scale-Invariant Feature Transform) algorithm often faces challenges under adverse conditions, such as a high number of mismatched points and few accurately matched points. Additionally, in practical scenarios, environmental factors like lighting changes and image blurring further reduce image similarity. Therefore, this paper proposes an improved SIFT-based image matching algorithm to address these challenges. First, SIFT is used to extract image features, and a bidirectional FLANN (Fast Library for Approximate Nearest Neighbors) matching strategy is employed to initially filter out incorrect features. Then, the RANSAC (Random Sample Consensus) algorithm is used to screen out unreliable matching point pairs. Finally, the matching accuracy is evaluated based on the remaining pure matching point pairs. Experimental results demonstrate that, compared to the traditional SIFT algorithm, this improved algorithm achieves higher matching accuracy and robustness under adverse conditions, exhibiting superior performance.

关键词： Location awareness Matched filters Accuracy Image matching Lighting Transforms Feature extraction Robustness Libraries Information technology

来源：评论

学校读者我要写书评

暂无评论

DETECTING MACHINE-GENERATED TEXTS BY MULTI-POPULATION AWARE OPTIMIZATION FOR MAXIMUM MEAN DISCREPANCY

arXiv

引用

arXiv 2024年

作者： Zhang, Shuhai Song, Yiliao Yang, Jiahao Li, Yuanqing Han, Bo Tan, Mingkui South China University of Technology China Pazhou Laboratory China The University of Adelaide Australia Key Laboratory of Big Data and Intelligent Robot Ministry of Education Department of Computer Science Hong Kong Baptist University Hong Kong

Large language models (LLMs) such as ChatGPT have exhibited remarkable performance in generating human-like texts. However, machine-generated texts (MGTs) may carry critical risks, such as plagiarism issues, misleading information, or hallucination issues. Therefore, it is very urgent and important to detect MGTs in many situations. Unfortunately, it is challenging to distinguish MGTs and human-written texts because the distributional discrepancy between them is often very subtle due to the remarkable performance of LLMs. In this paper, we seek to exploit maximum mean discrepancy (MMD) to address this issue in the sense that MMD can well identify distributional discrepancies. However, directly training a detector with MMD using diverse MGTs will incur a significantly increased variance of MMD since MGTs may contain multiple text populations due to various LLMs. This will severely impair MMD’s ability to measure the difference between two samples. To tackle this, we propose a novel multi-population aware optimization method for MMD called MMD-MP, which can avoid variance increases and thus improve the stability to measure the distributional discrepancy. Relying on MMD-MP, we develop two methods for paragraph-based and sentence-based detection, respectively. Extensive experiments on various LLMs, e.g., GPT2 and ChatGPT, show superior detection performance of our MMD-MP. The source code is available at https://***/ZSHsh98/MMD-MP. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Refining Idioms Semantics Comprehension via Contrastive Learning and Cross-Attention 30

Refining Idioms Semantics Comprehension via Contrastive Lear...

引用

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

作者： Wu, Mingmin Su, Guixin Zhang, Yongcheng Huang, Zhongqiang Sha, Ying College of Informatics Huazhong Agricultural University Wuhan China Key Laboratory of Smart Farming for Agricultural Animals Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education China

ISBN: (纸本)9782493814104

Chinese idioms on social media demand a nuanced understanding for correct usage. The Chinese idiom cloze test poses a unique challenge for machine reading comprehension due to the figurative meanings of idioms deviating from their literal interpretations, resulting in a semantic bias in models' comprehension of idioms. Furthermore, given that the figurative meanings of many idioms are similar, their use as suboptimal options can interfere with optimal selection. Despite achieving some success in the Chinese idiom cloze test, existing methods based on deep learning still struggle to comprehensively grasp idiom semantics due to the aforementioned issues. To tackle these challenges, we introduce a Refining Idioms Semantics Comprehension Framework (RISCF) to capture the comprehensive idioms semantics. Specifically, we propose a semantic sense contrastive learning module to enhance the representation of idiom semantics, diminishing the semantic bias between figurative and literal meanings of idioms. Meanwhile, we propose an interference-resistant cross-attention module to attenuate the interference of suboptimal options, which considers the interaction between the candidate idioms and the blank space in the context. Experimental results on the benchmark datasets demonstrate the effectiveness of our RISCF model, significantly outperforming state-of-the-art methods. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Propelling Pedagogical Paradigms: A Study of Advanced Human-Computer Interaction Learning in data Structure and Algorithms Based on Virtual Reality Technology 18th

Propelling Pedagogical Paradigms: A Study of Advanced Human-...

引用

18th International Conference on Computer Science and Education, ICCSE 2023

作者： Yahui, Yang Yanxia, Gao Ling, Peng Yingxi, Xiang Huan, He Yiwen, Liu School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China School of Fine Arts and Design Huaihua University Hunan Huaihua418000 China

ISBN: (纸本)9789819707362

data Structure and Algorithms (DSA) is a course with strong practice and abstract theoretical knowledge. In view of the complexity of the knowledge points of the course and the difficulty of understanding, we design and implement a virtual simulation experiment teaching system of the course--Virtual simulation experiment platform. In this platform, DSA through simulation practice into animation effects, and combined with the unity engine and C# code to achieve user interaction, to provide users with a way to intuitively understand the principles of DSA, while increasing the user’s subjective initiative to learn, and to achieve the high level, Innovative and challenging teaching classroom, so that students in colleges and universities can feel relaxed and happy in the process of learning this course. What is more, they can better accept and understand DSA. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： data structures

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：