检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Appicharla, Ramakrishna Gain, Baban Pal, Santanu Ekbal, Asif Bhattacharyya, Pushpak Department of Computer Science and Engineering Indian Institute of Technology Patna India Wipro AI Lab45 London United Kingdom School of AI and Data Science Indian Institute of Technology Jodhpur India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies (Li et al., 2020) have shown that the context encoder generates noise and makes the model robust to the choice of context. This paper further investigates this observation by explicitly modelling context encoding through multi-task learning (MTL) to make the model sensitive to the choice of context. We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. Generation of the source from the context is considered an auxiliary task, and generation of the target from the source is the main task. We experimented with German–English language pairs on News, TED, and Europarl corpora. Evaluation results show that the proposed MTL approach performs better than concatenation-based and multi-encoder DocNMT models in low-resource settings and is sensitive to the choice of context. However, we observe that the MTL models are failing to generate the source from the context. These observations align with the previous studies, and this might suggest that the available document-level parallel corpora are not context-aware, and a robust sentence-level model can outperform the context-aware models. © 2024, CC0.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

DSLA 2023 Facing the dangers of data illiteracy

引用

Significance 2023年第5期20卷 26-29页

作者： Gascon, Gregg M. Wallman, Katherine K. Ravula, Sridhar Cappelleri, Joseph C. Lee, Julia Lum, Kristian Nagaraja, Chaitra H. Paul, Sudeshna Roy, Dooti Wu, Edward The Department of Biomedical Informatics The Ohio State University College of Medicine United States United States The Human Relations Area Files The Yale University United States The Statistical Research and Data Science Center Pfizer Inc United States The Division of Biostatistics Department of Preventive Medicine the Feinberg School of Medicine Northwestern University United States The Data Science Institute University of Chicago United States The Department of Mathematics and Statistics University of Exeter United Kingdom The School of Nursing Emory University United States Boehringer Ingelheim Inc. United States The Social and Decision Analytics Division The Biocomplexity Institute University of Virginia United States

The data science and Literacy Act (DSLA) of 2023 aims to boost data literacy and data science education across the USA. Gregg M. Gascon, Katherine K. Wallman, Sridhar Ravula, Joseph Cappelleri, Julia Lee, Kristian Lum, Chaitra H. Nagaraja, Sudeshna Paul, Dooti Roy and Edward Wu explain why this opportunity demands our attention © 2023 Blackwell Publishing Ltd. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An end-to-end Flight Control Method for UAVs Based on MD-SAC

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Song, Chao Zhang, Yi Bai, Shuangxia Li, Bo Gan, Zhigang Neretin, Evgeny Northwestern Polytechnical University School of Electronics and Information Shaanxi Xi'an China School of Data Science City University of Hong Kong Hong Kong Shanghai Huawei Technologies Co. Ltd Shanghai China School of Moscow Aviation Institute Russia

Deep reinforcement learning (DRL) allows unmanned aerial vehicles (UAVs) to learn control policies for tasks in complicated and unfamiliar environments, hence it is widely employed in the field of UAV flight control. However, the model and operational environment of UAVs are typically simplified, rendering them unrepresentative of the real world. Furthermore, using only a single sensory data to control UAV flight is difficult to realize autonomous decision-making of UAVs. In this paper, an end-to-end flight control method for UAVs based on multimodal data fusion and Soft Actor-Critic (SAC) algorithm is proposed, named MD-SAC. First, this paper constructs the UAV model that is basically consistent with the real physical model, and forms a UAV multidata fusion state space including UAV information, UAV and target information and UAV sensor sensing information. Then, the strategy of directly mapping the multimodal data fusion results to the UAV torque and thrust is proposed to construct an end-to-end UAV hierarchical control model, and the convergence of the control method is accelerated based on the empirical playback mechanism. The experimental results show that the UAV based on the MD-SAC algorithm can effectively complete autonomous trajectory planning and adapt to a variety of complex environments, and the performance is improved in terms of robustness and generalization compared with the PPO algorithm and the optimized SAC algorithm. © 2025 IEEE. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Balancing Accuracy and Interpretability: An R Package Assessing Complex Relationships Beyond the Cox Model and Applications to Clinical Prediction

SSRN

引用

SSRN 2024年

作者： Shamsutdinova, Diana Stamate, Daniel Stahl, Daniel Department of Biostatistics and Health Informatics Institute of Psychiatry Psychology and Neuroscience King’s College London London United Kingdom Data Science and Soft Computing Lab Computing Department Goldsmiths University of London United Kingdom School of Health Sciences University of Manchester Manchester United Kingdom

BackgroundAccurate and interpretable models are essential for clinical decision-making, where predictions can directly impact patient care. Machine learning (ML) survival methods can handle complex multidimensional data and achieve high accuracy but require post-hoc explanations. Traditional models such as the Cox Proportional Hazards Model (Cox-PH) are less flexible, but fast, stable, and intrinsically transparent. Moreover, ML does not always outperform Cox-PH in clinical settings, warranting a diligent model validation. We aimed to develop a set of R functions to help explore the limits of Cox-PH compared to the tree-based and deep learning survival models for clinical prediction modelling, employing ensemble learning and nested *** developed a set of R functions, publicly available as the package "survcompare". It supports Cox-PH are Cox-Lasso, and Survival Random Forest (SRF) and DeepHit are the ML alternatives, along with the ensemble methods integrating Cox-PH with SRF or DeepHit designed to isolate the marginal value of ML. The package performs a repeated nested cross-validation and tests for statistical significance of the ML’s superiority using the survival-specific performance metrics, the concordance index, time-dependent AUC-ROC and calibration *** get practical insights, we applied this methodology to clinical and simulated datasets with varying complexities and *** simulated data with non-linearities or interactions, ML models outperformed Cox-PH at sample sizes ≥500. ML superiority was also observed in imaging and high-dimensional clinical data. However, for tabular clinical data, the performance gains of ML were minimal;in some cases, regularised Cox-Lasso recovered much of the ML’s performance advantage with significantly faster computations. Ensemble methods combining Cox-PH and ML predictions were instrumental in quantifying Cox-PH’s limits and improving ML calibration. Traditional models like Cox-PH or Cox

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DFS-NER: Description Enhanced Few-shot NER via Prompt Learning and Meta-Learning

DFS-NER: Description Enhanced Few-shot NER via Prompt Learni...

引用

2022 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Huinan Huang Yuming Feng Xiaolong Jin Saiping Guan Jiafeng Guo School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences

Named Entity Recognition (NER) is a very common task in many social good related domains. Recently, deep learning based NER has gradually matured, but still faces the scarcity problem of labeled data in specific domains. Therefore, researchers focus on few-shot NER to reduce the model’s data dependence and enhance the transferability of the model. However, existing works usually cannot adapt to new entity types and are prone to the so-called negative transfer problem. Therefore, in this paper we propose a type- Description-enhanced Few Shot NER model, called DFS-NER, which effectively integrates the prompt learning paradigm and the meta-learning framework. DFS-NER performs well under frozen pre-training model parameters through continuous templates. It realizes efficient source domain training and target domain parameter fine-tuning through the metalearning framework. We enhance the robustness of entity- type prototype representations by introducing word-word- level and word-type-level contrastive learning objectives and capsule networks as the induction module. Simultaneously, based on discrete prompt learning, a masked-language model learning objective guided by type description is proposed, which can well absorb the semantic information of entity types. Experiments on commonly used datasets, including, SNIPS, Few-NERD, and MIT Movie show that DFS-NER basically surpasses baseline models and achieves the state-of-the-art performance.

关键词： Deep learning Training Adaptation models Analytical models Semantics Prototypes Robustness

来源：评论

学校读者我要写书评

暂无评论

Spectral Clustering for Discrete Distributions

arXiv

引用

arXiv 2024年

作者： Wang, Zixiao Qiao, Dong Fan, Jicong School of Data Science The Chinese University of Hong Kong Shenzhen 2001 Longxiang Boulevard Longgang District Guangdong Shenzhen518172 China Shenzhen Research Institute of Big Data 2001 Longxiang Boulevard Longgang District Shenzhen518172 China

The discrete distribution is often used to describe complex instances in machine learning, such as images, sequences, and documents. Traditionally, clustering of discrete distributions (D2C) has been approached using Wasserstein barycenter methods. These methods operate under the assumption that clusters can be well-represented by barycenters, which is seldom true in many real-world applications. Additionally, these methods are not scalable for large datasets due to the high computational cost of calculating Wasserstein barycenters. In this work, we explore the feasibility of using spectral clustering combined with distribution affinity measures (e.g., maximum mean discrepancy and Wasserstein distance) to cluster discrete distributions. We demonstrate that these methods can be more accurate and efficient than barycenter methods. To further enhance scalability, we propose using linear optimal transport to construct affinity matrices efficiently for large datasets. We provide theoretical guarantees for the success of our methods in clustering distributions. Experiments on both synthetic and real data show that our methods outperform existing baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Formal Specification and Verification of API Security Based on Design by Contract

Formal Specification and Verification of API Security Based ...

引用

IEEE International Conference on Power, Intelligent computing and Systems (ICPICS)

作者： Qing Tang Zetong Zhou Zhaoxiong Bu Li Ma Yong Zhong Guangdong Chankong Big Data Technology Co. Ltd. Foshan China School of Management Guangdong University of Technology Foshan China School of Electronic and Information Engineering Foshan University Foshan China School of Electronic and Information Engineering Foshan University Zhixin Urban Big Data Technology Research Institute Foshan China Foshan Data Science Association School of Electronic and Information Engineering Foshan University Zhixin Urban Big Data Technology Research Institute Foshan China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

The exploitation and hijacking of API vulnerabilities are becoming increasingly prominent issues in software supply chain security. This paper proposes an Object-Z based formal verification method for APIs in the supply chain, aiming to address the security risks associated with API applications. By incorporating the concept of design by contract and using Object-Z for formal modeling, a dynamic defense against API threats is implemented. Finally, based on a classification analysis of API threats in the supply chain, this paper presents a ase study through modeling and application analysis.

关键词： Analytical models Computational modeling Supply chains Software Security Formal specifications Contracts Formal verification

来源：评论

学校读者我要写书评

暂无评论

Multipliers of Dirichlet-Type Subspaces of Weighted Bloch Spaces

引用

数学研究 2022年第3期55卷 229-241页

作者： Conghui Shen Jingshi Xu College of Mathematics and Data Science Minjiang UniversityFuzhou 350108China Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation School of Mathematics and Computing ScienceGuilin University of Electronic TechnologyGuilin 541004China.

In this paper,we characterize the multipliers on the intersection of the Diri-chlet-type space and the logarithmic Bloch space,and the intersection of the Dirichlet-type space and the logarithmic space of analytic fun... 详细信息

关键词： Multiplier Carleson measure Dirichlet-type space weighted Bloch space

来源：评论

学校读者我要写书评

暂无评论

FLOW-TSVAD: TARGET-SPEAKER VOICE ACTIVITY DETECTION VIA LATENT FLOW MATCHING

arXiv

引用

arXiv 2024年

作者： Chen, Zhengyang Han, Bing Wang, Shuai Jiang, Yidi Qian, Yanmin AudioCC Lab CS Dept Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore

Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm and our proposed Flow-TSVAD method outperforms the Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, requiring only two inference steps to achieve promising results. As a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times. Moreover, ensembling results from various sampling instances further enhances diarization performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Network-Based User Identification and data Cross-Referencing in XR Physical Spaces

Wireless Sensor Network-Based User Identification and Data C...

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Yu Cho Rong Kim Hye Sun Hong Sungujn Gil Youn Hee Um Tai Won Content Research Section Electronics and Telecommunications Research Institute Daejeon South Korea Graduate School of Data Science Chonnam National University Gwangju South Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

This paper presents the development and implementation of a wireless sensor network for real-time user identification and cross-referencing of sensor data between users in extended reality (XR) environments. The wireless sensor network system is designed to reference camera data from multiple users located within the same physical space. The proposed sensor network is connected in a full mesh configuration and utilizes Wi-Fi 6 technology and the BATMAN (Better Approach To Mobile Adhoc Networking) protocol, allowing for efficient user identification and seamless exchange of sensor data, even in complex environments.

关键词： Wireless communication Wireless sensor networks Extended reality System performance Prototypes Telecommunication traffic Cameras Wireless fidelity Thermal stability Testing

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：