检索结果-内蒙古大学图书馆

How nouns surface as verbs: Inference and generation in word class conversion 42

How nouns surface as verbs: Inference and generation in word...

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Yu, Lei El Sanyoura, Lana Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

Word class conversion refers to the extended use of a word from one grammatical class to another without overt morphological marking. Noun-to-verb conversion, or denominalization, is one form of word class conversion studied extensively in the literature. Previous work has suggested that novel denominal verb usages are comprehensible if the listener can compute the intended meaning based on shared knowledge with the speaker. However, no existing work has explored the computational mechanism under this proposal. We propose a frame-semantic generative model, Noun2Verb, that supports the inference and generation of novel denominal verb usages via semi-supervised learning. We evaluate this framework in a dataset of denominal verbs drawn from adults and children against a state-of-the-art model from natural language processing. Our results show that Noun2Verb aligns better with human interpretation and bridges the gap between machines and humans in lexical innovation. © 2020 The Author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Neural Rendering and Flow-assisted Unsupervised Multi-view Stereo for Real-time Monocular Tracking and Scene Perception

引用

IEEE Transactions on Automation science and engineering 2025年

作者： Tong, Kevin W. Cai, Yandong Jie, Yu-Wen Duan, Ya Hou, Yuhong Wu, Edmond Q. Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China Shanxi University School of Automation and Software Engineering Shanxi 237016 China Flight Test Technology and Engineering Center of the Chinese Flight Test Establishment Xian710089 China China Civil Aviation Shanghai Aircraft Airworthiness Certification Center Shanghai200335 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

The existing camera tracking and perception methods mainly rely on sparse SLAM, which limits the dense perception ability of the scene and affects the reliability of auxiliary decision-making. Different from this, this work proposes a real-time tracking and unsupervised dense sensing framework. Firstly, the dense depth value of the scene is predicted by unsupervised multi-view stereo to remove the dependence on labeled data. Then, the quality of synthetic pseudo-reference image is quantified according to the predicted depth map and used as a weighted guidance to train the unsupervised model, thus reducing the ambiguity of feature matching in areas such as specular reflection. Moreover, the sparse optical flow of the keyframes is solved by real-time and robust ORB feature matching operator, which assists the high-precision training of unsupervised depth inference model. To increase the prediction accuracy of occluded area, a novel rendering consistency loss via neural radiance fields is designed to constrain the geometric characteristics of object surface. Finally, dense direct image alignment is performed from a global model to improve the tracking robustness, which is incrementally constructed from dense depth prediction. Extensive experiments on synthetic datasets and real datasets validate the effectiveness and practicability of the proposed work, which is an effective supplement to the existing SLAM work. © 2025 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

EXTENDED PERSON-MACHINE INTERFACE

引用

ARTIFICIAL INTELLIGENCE 1984年第2期22卷 157-218页

作者： REICHMANADAR, R Department of Electrical Engineering and Computer Science Institute for Cognitive Science University of California La Jolla CA 92093 U.S.A

Current computer natural language systems lack discourse capabilities. They mainly treat utterances in isolation and are not able to track the coherence of extended dialogue. In general, however, human communication and task performance are not accomplished in this manner. Useful interface systems should incorporate extended conversational power. In this paper, we present an abstract computational system for extended person-machine interface. The system is theoretically motivated by an investigation into the human conversational system. The computer system incorporates many of the rules used by individuals in everyday interactions. Use of these rules enable implicit communication between conversants about their underlying models of an interaction. They function in place of explicit meta-communication about the structure of an ongoing exchange. Such communication is necessary since building compatible models of an interaction is necessary for effective interaction. Providing a comparable system of rules for the computer is then mandatory if we expect it to be able to integrate subsequent requests and exchanges to earlier ones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolvable dialogue state tracking for statistical dialogue management

引用

Frontiers of computer science 2016年第2期10卷 201-215页

作者： Kai YU Lu CHEN Kai SUN Qizhe XIE Su ZHU Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive EngineeringSpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Department of Computer Science Cornell University Ithaca NY 14853 USA

Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.

关键词： dialogue management domain extension,evolvable dialogue state tracking parser tracker

来源：评论

学校读者我要写书评

暂无评论

IMPROVING WORLD MODELS USING DEEP SUPERVISION WITH LINEAR PROBES

arXiv

引用

arXiv 2025年

作者： Zahorodnii, Andrii Department of Electrical Engineering and Computer Science MIT United States Department of Brain and Cognitive Sciences McGovern Institute for Brain Research MIT CambridgeMA United States

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model in a network trained end-to-end to predict the next observation. While deep supervision has been widely applied for task-specific learning, our focus is on improving the world models. Using an experimental environment based on the Flappy Bird game, where the agent receives only LIDAR measurements as observations, we explore the effect of adding a linear probe component to the network’s loss function. This additional term encourages the network to encode a subset of the true underlying world features into its hidden state. Our experiments demonstrate that this supervision technique improves both training and test performance, enhances training stability, and results in more easily decodable world features – even for those world features which were not included in the training. Furthermore, we observe a reduced distribution drift in networks trained with the linear probe, particularly during high-variability phases of the game (flying between successive pipe encounters). Including the world features loss component roughly corresponded to doubling the model size, suggesting that the linear probe technique is particularly beneficial in compute-limited settings or when aiming to achieve the best performance with smaller models. These findings contribute to our understanding of how to develop more robust and sophisticated world models in artificial agents, paving the way for further advancements in this field. 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

A computational evaluation of gender asymmetry in semantic change 43

A computational evaluation of gender asymmetry in semantic c...

引用

43rd Annual Meeting of the cognitive science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Schnell, Eric Xu, Yang Cognitive Science and Mathematics Programs University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

A fundamental goal in cognitive and historical linguistic research on semantic change is to characterize the regularity in how word meanings change over time. We examine a common belief that has not yet been evaluated comprehensively, which asserts that gender of a word influences its direction of semantic change. By this account, female terms like mistress should undergo pejorative change in meaning systematically more so than male terms like master. We evaluate this claim in gender-marked word pairs in English and French respectively as languages without and with grammatical gender. Our results provide supporting evidence for gender asymmetry in semantic change of English words but not French words. Our study raises questions about the generality of the claim about gender asymmetry in semantic change and provides a scalable computational framework for understanding the social roots of word meaning change. © cognitive science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Monitoring blood pressure through a single hybrid hemodynamic signal with a flexible optoelectronic patch

Device

引用

Device 2025年

作者： Zhong, Yizhou Zhang, Yongcao Pu, Jing Wustoni, Shofarul Uribe, Johana Lopez-Larrea, Naroa Marks, Adam McCulloch, Iain Mecerreyes, David Baran, Derya Inal, Sahika Organic Bioelectronics Laboratory Biological and Environmental Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Materials Science and Engineering Program (MSE) Physical Sciences and Engineering Division (PSE) KAUST Thuwal 23955-6900 Saudi Arabia POLYMAT University of the Basque Country UPV/EHU Avenida Tolosa 72 Guipuzcoa Donostia-San Sebastian 20018 Spain Department of Chemistry University of Oxford Oxford OX1 3TF United Kingdom Andlinger Center for Energy and the Environment and Department of Electrical and Computer Engineering Princeton University Princeton 08544 NJ United States IKERBASQUE Basque Foundation for Science Plaza Euskadi 5 Bilbao 48009 Spain

Hemodynamics, the study of blood flow and circulatory forces, is fundamental for assessing cardiovascular health, disease states, and therapeutic outcomes. Here, we introduce a skin-conformable organic optoelectronic thin-film patch (ePatch) designed to simultaneously capture electrocardiography (ECG) and photoplethysmography (PPG) signals as a single hybrid signal, named the electrocardio-photoplethysmogram (EC-PPG). The ePatch integrates an organic electrochemical transistor (OECT), an organic photodiode, surface-mounted light-emitting diodes, and electrochemical electrodes on a flexible, skin-conforming substrate. By training deep learning models on the hybrid EC-PPG data, we achieved accurate arterial blood pressure estimations, with mean errors of just 1.69 mmHg for systolic and 0.89 mmHg for diastolic blood pressure, outperforming traditional predictions that rely on individual physiological signals as inputs. Our findings underscore the potential of EC-PPG as a compound hemodynamic signal for AI-driven vital sign monitoring and integrated, solution-processable soft electronics for clinical and point-of-care applications. © 2025 The Authors

关键词： DTI-3: Develop electrocardiography electrophysiology flexible electronics OECT OPD organic electrochemical transistor photoplethysmography wearable electronics

来源：评论

学校读者我要写书评

暂无评论

Coalition Formation for Heterogeneous Federated Learning Enabled Channel Estimation in RIS-assisted Cell-free MIMO

arXiv

引用

arXiv 2025年

作者： Qi, Nan Liu, Haoxuan Tsiftsis, Theodoros A. Boulogeorgos, Alexandros-Apostolos A. Zhou, Fuhui Jin, Shi Wu, Qihui Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Informatics and Telecommunications University of Thessaly Lamia35100 Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani50100 Greece National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China

Downlink channel estimation remains a significant bottleneck in reconfigurable intelligent surface-assisted cell-free multiple-input multiple-output communication systems. Conventional approaches primarily rely on centralized deep learning methods to estimate the high-dimensional and complex cascaded channels. These methods require data aggregation from all users for centralized model training, leading to excessive communication overhead and significant data privacy concerns. Additionally, the large size of local learning models imposes heavy computational demands on end users, necessitating strong computational capabilities that most commercial devices lack. To address the aforementioned challenges, a coalition-formation-guided heterogeneous federated learning (FL) framework is proposed. This framework leverages coalition formation to guide the formation of heterogeneous FL user groups for efficient channel estimation. Specifically, by utilizing a distributed deep reinforcement learning (DRL) approach, each FL user intelligently and independently decides whether to join or leave a coalition, aiming at improving channel estimation accuracy, while reducing local model size and computational costs for end users. Moreover, to accelerate the DRL-FL convergence process and reduce computational burdens on end users, a transfer learning method is introduced. This method incorporates both received reference signal power and distance similarity metrics, by considering that nodes with similar distances to the base station and comparable received signal power have a strong likelihood of experiencing similar channel fading. Massive experiments performed that reveal that, compared with the benchmarks, the proposed framework significantly reduces the computational overhead of end users by 16%, improves data privacy, and improves channel estimation accuracy by 20%. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Role of high energy photons in dual spectral source rapid isothermal CVD

引用

JOURNAL OF ELECTRONIC MATERIALS 1997年第10期26卷 1184-1188页

作者： Singh, R Chen, Y Department of Electrical and Computer Engineering Material Science and Engineering Program Clemson University Clemson Department of Electrical and Computer Engineering Clemson University Clemson

The use of tungsten halogen lamps and the deuterium lamp as the source of thermal and optical energies has been exploited to deposit thin films of Ta2O5 on Si and conducting substrates, The leakage current densities are as low as 10(-10) A/cm(2) for gate voltage under 5V. Photons in visible, ultraviolet, and vacuum ultraviolet (lambda < 800 nm) regions provide higher bulk and surface diffusion coefficients as well as reduced activation energy for the chemical process involved in the chemical vapor deposition process. The low thermal mass of the substrate provides limited reaction processing capability. The photochemical and photophysical processes allow the participating atoms and molecules to adjust their bond geometries and occupy sites which result in overall reduction of stress and strain energy and provide materials with overall low microscopic defects at low processing temperature and with high throughput. New experimental results of Al-Ta2O5-Si3N4-poly Si-Al structure are presented. The leakage current-voltage characteristics are better than those reported by other researchers.

关键词： dielectrics metalorganic chemical vapor deposition (MOCVD) rapid isothermal processing (RIP) Ta2O5

来源：评论

学校读者我要写书评

暂无评论

TextAI 3.0 (Multimodal): multimodal sentiment analysis using attention-enabled ensemble-based deep learning in hyperbolic space

引用

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： Singh, Jaskaran Sanga, Prabhav Khanna, Narendra N. Laird, John R. Singh, Inder M. Kalra, Mannudeep K. Mantella, Laura E. Johri, Amer M. Faa, Gavino Tiwari, Ekta Singh, Rajesh Abbas, Mohamed Saba, Luca Suri, Jasjit S. Stroke Monitoring and Diagnostic Division AtheroPoint™ Roseville 95661 CA United States Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Cardiology Indraprastha APOLLO Hospitals New Delhi 110001 India Department of Neurology and Stroke Program University of Maryland School of Medicine Baltimore United States Department of Radiology Harvard Medical School Boston 02115 MA United States Department of Biomedical and Molecular Sciences Queen’s University Kingston ON Canada Division of Cardiology Department of Medicine Queen’s University Kingston ON Canada Department of Pathology University of Cagliari Cagliari Italy Department of Computer Science Visvesvaraya National Institute of Technology (VNIT) Nagpur 440010 India Department of Research and Innovation Uttaranchal Institute of Technology Uttaranchal University Dehradun 248007 India Central Labs King Khalid University P.O. Box 960 AlQura’a Abha Saudi Arabia Electrical Engineering Department College of Engineering King Khalid University Abha 61421 Saudi Arabia Department of Neurology University of Cagliari Cagliari Italy Department of ECE Idaho State University Pocatello 83209 ID United States Department of CE Graphic Era Deemed to Be University Dehradun 248002 India University Center for Research and Development Chandigarh University Mohali India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Campus Pune India Department of Innovation Global Biomedical Technologies Inc. Roseville 95661 CA United States

The rising prevalence of depression presents a significant global health challenge, underscoring the need for effective early detection through sentiment analysis. Traditional multimodal sentiment analysis methods, which rely on Euclidean space for data representation, often fail to capture the complex hierarchical relationships and non-linear structures inherent in multimodal data. To address this limitation, we propose a novel multimodal architecture that operates in hyperbolic space and incorporates attention-based ensemble learning to enhance feature representation and model performance. We developed and evaluated ten AI models—five utilizing Euclidean space and five leveraging hyperbolic space—on the Spoken Language Understanding Evaluation (SLUE) benchmark dataset. The models were assessed using cross-validation techniques to ensure robustness, and statistical analyses were conducted to validate the findings. Our results indicate that hyperbolic-based multimodal models achieve a 2.32% improvement in accuracy compared to their Euclidean counterparts, while the integration of self-attention mechanisms further contributes an average accuracy gain of 0.96%. Additionally, we observed a 3.76% decline in performance when reducing the training-to-test data ratio from 90:10 to 50:50, highlighting the importance of data distribution in model training. These findings confirm that attention-enhanced multimodal models in hyperbolic space offer superior representations for sentiment analysis. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Attention-enabled Deep learning Euclidean space Hyperbolic space Multimodal Sentiment analysis

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：