检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic-Preserving Adversarial Code Comprehension

arXiv

引用

arXiv 2022年

作者： Li, Yiyang Wu, Hongqiu Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the tradeoff between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code1 © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Audio-visual multimodal speech recognition method fusing audio and video data 2

Audio-visual multimodal speech recognition method fusing aud...

引用

2nd International Conference on Digital Signal and computer Communications, DSCC 2022

作者： Zhao, Jian Zhang, Zhiwei Cui, Yuqing Qiang, Wenqian Dai, Weiqiang Kuang, Zhejun Shi, Lijuan Changchun University Department of Computer Science and Technology Changchun130022 China Jilin Provincial Key Laboratory of Human Health Status Identification and Function Enhancement Changchun130022 China Changchun University Department of Electronic Information Engineering Changchun130022 China Changchun University Cyberspace Security System Changchun130022 China

ISBN: (纸本)9781510656734

With the widespread application of deep learning methods, multimodal techniques have also achieved rapid development. Since single-modal speech recognition may affect the accuracy of recognition results in noisy environments, multimodal fusion recognition gradually replaces the traditional single-modal recognition methods. In this paper, we mainly strengthen and pre-process audio and video data first, and use LSTM recurrent neural network for deep feature extraction of audio and video streams, which effectively solves the problem of long-term forgetting of general neural networks. The audio and video feature vectors are then fused by a fully connected neural network with linear connections. Compared with the speech recognition technique alone, this audiovisual fusion recognition method has a better recognition effect in the case of noise interference. Compared with the traditional audiovisual recognition method, the model simplifies the recognition work. Recognition experiments on the LRS2-BBC dataset show that the recognition accuracy of this method improves to a certain extent over that of other methods in a clean environment and greatly improves in noisy conditions. © 2022 SPIE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Generative or Contrastive? Phrase Reconstruction for Better Sentence Representation Learning

arXiv

引用

arXiv 2022年

作者： Wu, Bohong Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised learning can be distinguished into two subcategories, generative and contrastive, then most existing studies show that sentence representation learning may more benefit from the contrastive methods but not the generative methods. However, contrastive learning cannot be well compatible with the common token-level generative self-supervised learning, and does not guarantee good performance on downstream semantic retrieval tasks. Thus, to alleviate such obvious inconveniences, we instead propose a novel generative self-supervised learning objective based on phrase reconstruction. Empirical studies show that our generative learning may yield powerful enough sentence representation and achieve performance in Sentence Textual Similarity (STS) tasks on par with contrastive learning. Further, in terms of unsupervised setting, our generative method outperforms previous state-of-the-art SimCSE on the benchmark of downstream semantic retrieval tasks. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sentence Representation Learning with Generative Objective rather than Contrastive Objective

arXiv

引用

arXiv 2022年

Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However, contrastive objectives which dominate the current sentence representation learning bring little linguistic interpretability and no performance guarantee on downstream semantic tasks. We instead propose a novel generative self-supervised learning objective based on phrase reconstruction. To overcome the drawbacks of previous generative methods, we carefully model intra-sentence structure by breaking down one sentence into pieces of important phrases. Empirical studies show that our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods not only on the STS benchmarks, but also on downstream semantic retrieval and reranking tasks. Our code is available at https://***/chengzhipanpan/PaSeR. Copyright © 2022, 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

Deep Learning based Intelligent Spectrum Sensing Framework Optimizing Dynamic Radio Resource Allocation

Deep Learning based Intelligent Spectrum Sensing Framework O...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Ravi Kumar M Mahesh Kumar A. S Abbas Thajeel Rhaif Alsahlanee Bhargav H K Amit Barve Abhijit Mitra Department of Electronics and Communication Engineering Cambridge Institute of Technology Bengaluru India Department of Electronics and Communication Engineering Maharaja Institute of Technology Mysore India Faculty of Education for Human Sciences University of Thi-Qar Nasiriyah Iraq Deptartment of Computer Science and Engineering Shridevi Institute of Engineering and Technology Industry Institute Interaction Cell (IIIC) Tumakuru India Department of Computer Science and Engineering Parul Institute of Technology Faculty of Engineering and Technology Parul University India Symbiosis Centre for Advanced Legal Studies and Research (SCALSAR) Symbiosis Law School Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Efficient spectrum utilization in today's wireless communications requires intelligent spectrum sensing because dynamic spectrum access depends on it for resource allocation. This study presents a new deep learning framework for spectrum sensing which uses convolutional neural networks together with long short-term memory networks. Decision-making processes in real-time employ hybrid architecture which analyses both spectrum data spatial patterns as well as its temporal evolution through reinforcement learning mechanisms. The spectrum sensing framework using deep learning achieved 97.8% accuracy in detecting spectrum holes while reaching 95.3% precision in identifying primary users through its implementation which resulted in a 42% better spectrum utilization than conventional energy detection methods. Under -20dB to 20dB SNR conditions the system maintained steady performance that generated false alarms less than 0.03 times per observation. The proposed system design provides improved spectrum detection capabilities and resource distribution capabilities which makes it applicable for on-going wireless networks in congested urban spaces.

关键词： Deep learning Accuracy Wireless networks computer architecture Dynamic scheduling Spatial databases Sensors Resource management Convolutional neural networks System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Learning Better Masking for Better Language Model Pre-training

arXiv

引用

arXiv 2022年

作者： Yang, Dongjie Zhang, Zhuosheng Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Masked Language Modeling (MLM) has been widely used as the denoising objective in pretraining language models (PrLMs). Existing PrLMs commonly adopt a Random-Token Masking strategy where a fixed masking ratio is applied and different contents are masked by an equal probability throughout the entire training. However, the model may receive a complicated impact from pre-training status, which changes accordingly as training time goes on. In this paper, we show that such time-invariant MLM settings on masking ratio and masked content are unlikely to deliver an optimal outcome, which motivates us to explore the influence of time-variant MLM settings. We propose two scheduled masking approaches that adaptively tune the masking ratio and masked content in different training stages, which improves the pre-training efficiency and effectiveness verified on the downstream tasks. Our work is a pioneer study on time-variant masking strategy on ratio and content and gives a better understanding of how masking ratio and masked content influence the MLM pretraining1 Copyright © 2022, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Multidisciplinary integration of frontier technologies facilitating the development of anesthesiology and perioperative medicine in aging society

引用

Fundamental Research 2024年第4期4卷 795-796页

作者： Lize Xiong Junli Cao Hailong Dong Weihong Song Dong Ming Translational Research Institute of Brain and Brain-Like Intelligence and Department of Anesthesiology and Perioperative Medicine Shanghai Fourth People's Hospital Affiliated to Tongji University School of MedicineShanghai 200434China Jiangsu Province Key Laboratory of Anesthesiology Xuzhou Medical UniversityXuzhou 221004China Department of Anesthesiology and Perioperative Medicine Xijing Hospitalthe Fourth Military Medical UniversityXi'an 710032China The Second Affliated Hospital and Yuying Children's Hospital Institute of AgingKey Laboratory of Alzheimer's Disease of Zhejiang ProvinceWenzhou Medical UniversityWenzhou325035China State Key Laboratory of Advanced Medical Materials and Devices Medical SchoolTianjin UniversityTianjin 300072China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin 300380China

The population aged 60 and over in China reached approximately 297 million in 2023 according to the National Bureau of Statistics,accounting for 21.1%of the national *** population aged 65 and over was about 217 million,accounting for 15.4%[1].It is estimated that by 2035,China will have an elderly population of over 400 million,accounting for more than 30%of the total population,thereby entering a stage of severe *** brings many challenges to the society,especially in terms of medical care for elderly *** continuous advancement of science and technology,especially the breakthrough in basic research as well as new technologies and interdisciplinary integration,has brought new opportunities for the development of various professional *** better address the challenges of anesthesia and perioperative medicine in the aging era and to accelerate the rehabilitation of patients while maintaining life and health services,it is crucial to promote interdisciplinary integration.

关键词： breakthrough frontier thereby

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Optimization for Full-Duplex D2D Communications Underlaying Distributed Antenna Systems

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2024年

作者： Liu, Zhan Liao, Zhiyuan Li, Chunquan Zhang, Zhijun Yu, Junzhi Liu, P.X. Hunan University of Humanities Science and Technology School of Information Loudi417000 China Nanchang University School of Information Engineering Nanchang330031 China Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang330031 China South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

In this paper, we investigate the total system energy efficiency (EE) of full-duplex (FD) device-to-device (D2D) communications underlaying distributed antenna systems (DAS), where remote access units (RAUs), D2D users (DUs), and cellular users (CUs) are all capable of FD operation. Specifically, we jointly optimize subcarrier assignment and power allocation under the quality of service (QoS) requirements of CUs and DUs and the maximum power constraints of RAUs, CUs, and DUs. In addition, we propose a novel spectrum sharing strategy that allows each subcarrier to be assigned to multiple CUs and/or multiple D2D pairs (DPs) for flexibility. To solve the formulated non-convex optimization problem, we first employ fractional programming to transform the objective function in the optimization problem from the fractional form into the equivalent subtractive form. Then, an efficient iterative resource allocation algorithm is proposed, which needs to solve an inner problem in each iteration. After relaxing the variables and introducing penalty factors, the non-convex inner problem is transformed into a convex problem through the successive convex approximation (SCA) method and solved by iterative algorithm. Simulation results demonstrate that the proposed algorithm can considerably improve the system EE compared to other benchmark schemes. Furthermore, the proposed spectrum sharing strategy is superior to the existing sharing strategies. © 2017 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Adversarial Self-Attention for Language Understanding

arXiv

引用

arXiv 2022年

作者： Wu, Hongqiu Ding, Ruixue Zhao, Hai Xie, Pengjun Huang, Fei Zhang, Min Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China School of Computer Science and Technology Soochow University China Damo Academy Alibaba Group China

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a "shortcut" between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its robust variant for Transformer-based pre-trained language models (e.g. BERT). We propose Adversarial Self-Attention mechanism (ASA), which adversarially biases the attentions to effectively suppress the model reliance on features (e.g. specific keywords) and encourage its exploration of broader semantics. We conduct a comprehensive evaluation across a wide range of tasks for both pre-training and fine-tuning stages. For pre-training, ASA unfolds remarkable performance gains compared to naive training for longer steps. For fine-tuning, ASA-empowered models outweigh naive models by a large margin considering both generalization and robustness. Copyright © 2022, 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

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：