检索结果-内蒙古大学图书馆

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Graph Convolutional Neural Network for Object Recognition from Point Cloud data 2nd

Multi-scale Graph Convolutional Neural Network for Object Re...

引用

2nd International Conference on Urban Intelligence and Applications, ICUIA 2020

作者： Lu, Qiang Chen, Chao Teng, Jinfeng Zhang, Chunyuan Huang, Yi Xuan, Shanli Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China School of Computer and Information Hefei University of Technology Hefei230009 China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei230009 China

ISBN: (纸本)9789813346000

How to make robots understand the point cloud data which is collected from the 3D sensor and complete the recognition has become a hot research direction in recent years. In this paper, we propose a new approach to improve the critical robotic capability, semantic understanding of the environment (i.e., 3D object recognition). The convolutional neural network (CNN) method has a very good recognition result in the 2D image domain, but it has certain difficulty in applying irregular and unordered 3D point clouds data. The network for point cloud data generally uses the convolution to realize the extraction of point cloud features by finding the neighborhood features on the point set. Due to the different neighborhood scales caused by the irregularity of 3D point cloud data, we propose a CNN structure that combines multi-scale features. By finding multiple neighborhoods of the point set and establishing local graph extraction features, the stable expression of the local neighborhood is obtained. At the same time, the key point calibration method is added, so that the network can dynamically focus on key point features to improve the recognition result. In a series of analytical experiments, we demonstrate competing results that demonstrate the effectiveness of the network structure. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Personalized Recommendation Based On Entity Attributes and Graph Features

Personalized Recommendation Based On Entity Attributes and G...

引用

IEEE International Conference on big knowledge (ICBK)

作者： Yi Zhu Bingbing Dong Zhiqing Sha School of Information Engineering Yangzhou University Yangzhou China Ministry of Education Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Instituse of Big Knowledge Science Hefei University of Technology Hefei China

ISBN: (纸本)9781665438599

With the rapid increase in the amount of website data, it has been a more difficult task for users to get the infor-mation they are interested in. Personalized recommendation is an important bridge to find the information which users really need on the website. Many recent studies have introduced additional attribute information about users and/or items to the rating matrix for alleviating the problem of data sparsity. In order to make full use of the attribute information and scoring matrix, deep learning based recommendation methods are proposed, especially the autoencoder model has attracted much attention because of its strong ability to learn hidden features. However, most of the existing autoencoder- based models require that the dimension of the input layer is equal to the dimension of the output layer, which may increase model complexity and certain information loss when using attribute information. In addition, as users' awareness of privacy protection increases, user attribute information is difficult to obtain. To address the above problems, in this paper, we propose a hybrid personalized recommendation model, which uses a semi-autoencoder to jointly embed the item's score vector and internal graph features (short for Co-Agpre). Specifically, we regard the user-item historical interaction matrix as a bipartite graph, and the Laplacian of the user-item co-occurrence graph is utilized to obtain the graph features of the item for solving the problem of sparse attributes. Then a semi-autoencoder is introduced to learn the hidden features of the item and perform rating prediction. The proposed model can flexibly use information from different sources to reduce the complexity of the model. Experiments on two real-world datasets demonstrate the effectiveness of the proposed Co-Agpre compared with state-of-the-art methods.

关键词： Deep learning Privacy Laplace equations Conferences Predictive models Feature extraction Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Quaternion factorization machines: A lightweight solution to intricate feature interaction modelling

arXiv

引用

arXiv 2021年

作者： Chen, Tong Yin, Hongzhi Zhang, Xiangliang Huang, Zi Wang, Yang Wang, Meng The School of Information Technology and Electrical Engineering The University of Queensland Australia The Machine Intelligence and Knowledge Engineering Laboratory King Abdullah University of Science and Technology Saudi Arabia The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China

Due to the sparsity of available features in web-scale predictive analytics, combinatorial features become a crucial means for deriving accurate predictions. As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering. With the prominent development of deep neural networks (DNNs), there is a recent and ongoing trend of enhancing the expressiveness of FM-based models with DNNs. However, though better results are obtained with DNN-based FM variants, such performance gain is paid off by an enormous amount (usually millions) of excessive model parameters on top of the plain FM. Consequently, the heavy parameterization impedes the real-life practicality of those deep models, especially efficient deployment on resource-constrained IoT and edge devices. In this paper, we move beyond the traditional real space where most deep FM-based models are defined, and seek solutions from quaternion representations within the hypercomplex space. Specifically, we propose the quaternion factorization machine (QFM) and quaternion neural factorization machine (QNFM), which are two novel lightweight and memory-efficient quaternion-valued models for sparse predictive analytics. By introducing a brand new take on FM-based models with the notion of quaternion algebra, our models not only enable expressive inter-component feature interactions, but also significantly reduce the parameter size due to lower degrees of freedom in the hypercomplex Hamilton product compared with real-valued matrix multiplication. Extensive experimental results on three large-scale datasets demonstrate that QFM achieves 4.36% performance improvement over the plain FM without introducing any extra parameters, while QNFM outperforms all baselines with up to two magnitudes' parameter size reduction in comparison to state-of-the-art peer methods. Copyright © 2021, The Authors. All

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

knowledge Fragment Cleaning in a Genealogy knowledge Graph

Knowledge Fragment Cleaning in a Genealogy Knowledge Graph

引用

IEEE International Conference on big knowledge (ICBK)

作者： Guliu Liu Lei Li Key Laboratory of Knowledge Engineering with Big Data (Heifei Unversity of Technology) Ministry of Education Heifei China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

As an important topic of artificial intelligence, knowledge graphs have a wide range of applications such as semantic search, intelligent question answering, and visual decision support. Among them, the genealogy knowledge graph, as a kind of domain knowledge graph, has important application value in genetic disease analysis, population behavior analysis, etc. In the case of multiple data sources and multi-person collaboration, the construction of a genealogy knowledge graph involves the techniques of knowledge representation, knowledge acquisition, and knowledge fusion. In the knowledge fusion process, there are many situations such as the lack and chaos of a relationship, redundant entities, the isolation of some entities and knowledge fragments. How to effectively detect and process these problematic knowledge fragments is significant to the construction of a genealogy knowledge graph. In response to this problem, we propose a method for cleaning the problematic knowledge fragments in a genealogy knowledge graph. The method consists of three phases. In phase 1, we propose a method for detecting and analyzing the problematic knowledge fragments. In phase 2, we design a method for supplementing the entity-relationship of people for different error patterns and a method fusion method for the aligned entity. In phase 3, for the cleaning of isolated knowledge fragments, we propose an entity alignment method based on the father-son relationship and people's names and a connection method of isolated knowledge fragments. Finally, we conduct experiments on a family tree dataset of the Huapu System, and the experimental results indicate the effectiveness and practicality of the method.

关键词： Cleaning big data knowledge acquisition Redundancy Organizations databases

来源：评论

学校读者我要写书评

暂无评论

Neural Collaborative Recommendation with knowledge Graph

Neural Collaborative Recommendation with Knowledge Graph

引用

IEEE International Conference on big knowledge (ICBK)

作者： Lei Sang Lei Li Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

knowledge Graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem in recommender system. However, existing KG based recommendation methods mainly rely on handcrafted meta-path features or simple triple-level entity embedding, which cannot automatically capture entities' long-term relational dependencies for the recommendation. In this paper, a two-channel neural interaction method named knowledge Graph enhanced Neural Collaborative Filtering with Residual Recurrent Network (KGNCF-RRN) is proposed, which leverages both long-term relational dependencies KG context and user-item interaction for recommendation. (1) For the KG context interaction channel, we propose a Residual Recurrent Network (RRN) to construct context-based path embedding, which incorporates residual learning into traditional recurrent neural networks (RNNs) to efficiently encode the long-term relational dependencies of KG. The self-attention network is then applied to the path embedding to capture the polysemy of various user interaction behaviours. (2) For the user-item interaction channel, the user and item embeddings are fed into a newly designed two-dimensional interaction map. (3) Finally, above the two-channel neural interaction matrix, we employ a convolutional neural network to learn complex correlations between user and item. Extensive experimental results on three benchmark datasets show that our proposed approach outperforms existing state-of-the-art approaches for knowledge graph based recommendation.

关键词： Collaboration Recurrent neural networks knowledge engineering Semantics Motion pictures Context modeling Filtering

来源：评论

学校读者我要写书评

暂无评论

Delay-Sensitive Goods Delivery and In-Situ Sensing Using A Multi-Task Drone

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Bin Ni, Wei Liu, Ren Ping Guo, Y. Jay Zhu, Hongbo Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China Nanjing University of Posts and Telecommunications Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of Education Nanjing210003 China University of Technology Sydney Global Big Data Technologies Centre UltimoNSW Australia Barkhausen Institut Technische Universität Dresden Dresden Germany DATA61 CSIRO MarsfieldNSW2122 Australia

Drones are evolving into highly capable and adaptable devices, prompting the development of advanced control frameworks. This paper introduces a novel online control framework tailored for a multi-task drone, explicitly addressing the simultaneous execution of in-situ sensing and goods delivery. To tackle this complex scenario, a finite-horizon Markov decision process (FH-MDP) is formulated to ensure not only the prompt delivery of goods but also the minimization of energy consumption and the maximization of the drone's reward for in-situ sensing. A significant contribution lies in establishing the monotonicity and subadditivity of the FH-MDP. This mathematical foundation provides evidence for the existence of an optimal, monotone, deterministic Markovian policy. The crux of the optimal policy revolves around flight distance- and time-related thresholds, determining the precise points at which the drone should switch its optimal action. This unique feature empowers the multi-task drone to make real-time decisions, such as adjusting flight speed or engaging in in-situ sensing, by comparing its current state with these predefined thresholds. This process can be accomplished with a linear complexity, ensuring efficiency in decision-making. The optimality of our approach is rigorously demonstrated through numerical validation, where it is compared against a computationally expensive, dynamic programming-based alternative. Under the considered simulation settings, our approach reduces drone energy consumption by a substantial 19.8% compared to existing benchmarks. This not only highlights the practical effectiveness of the proposed framework but also underscores its potential for significant advancements in the field of drone operations and energy efficiency. © 2002-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Method for Updating Individual Tree Species Samples Based on Different Images

A Method for Updating Individual Tree Species Samples Based ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Caiyan Chen Linhai Jing Fulong Chen Hui Li Baoxin Hu Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing China International Research Center of Big Data for Sustainable Development Goals Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Poyang Lake Wetland and Watershed Research Ministry of Education & School of Geography and Environment Jiangxi Normal University Nanchang China Department of Earth and Space Science and Engineering York University Toronto Ontario Canada

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

The correct classification of individual tree species (ITS) is of great importance for forest resource management. However, current ITS samples collection is time-consuming and laborious in field surveys, and the samples cannot be updated in time. In this study, a sample update method is proposed, which updates samples by detecting the spectral angular similarity of samples at different times at the same location, enabling the reuse of historical samples and timely update of samples. Experimental results showed that the classification accuracy could reach more than 90% by using DenseNet model and the updated samples, which proved that the sample update method could achieve sample update and sample reuse effectively. In addition, there was significant improvement in the classification accuracy of the sample set using multispectral and texture information fusion, proving the effectiveness of information fusion in increasing classification information.

关键词： Surveys Accuracy Laser radar Soft sensors Geoscience and remote sensing Vegetation Forestry

来源：评论

学校读者我要写书评

暂无评论

GK: A Graphormer Architecture Based knowledge Graph Reasoning Model for Link Prediction

GK: A Graphormer Architecture Based Knowledge Graph Reasonin...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Yueiia Wu Jian-tao Zhou Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing College of Computer Science Inner Mongolia University National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China

knowledge Graph has become a dominant research field in graph theory, but its incompleteness and sparsity hinder its application in various fields. knowledge Graph Reasoning aims to alleviate these problems by deducing new knowledge or identifying false knowledge from existing knowledge. Recently, the Graph Convolution Network (GCN) based method is one of the most advanced methods to realize knowledge graph reasoning. However, it still suffers from some problems such as incomplete neighbor information aggregation and slow training speed. This paper proposes a knowledge graph reasoning model named GK for the link prediction task, which obtains better performance than existing GCN-based methods by introducing Graphormer into knowledge reasoning. The GK first proposes that nodes and their surroundings can be regarded as a hierarchical architecture that enables the model to capture more practical reasoning information to improve prediction accuracy. In addition, to accelerate the training speed of the model on the large-scale knowledge Graph, we present a faster shortest path-finding method F-SPF in the edge coding process. Extensive experimental results show that the GK model can obtain the state-of-the-art prediction results of current GCN-based methods and can improve the training speed.

关键词： Training knowledge engineering knowledge graphs Predictive models Prediction algorithms Feature extraction Cognition

来源：评论

学校读者我要写书评

暂无评论

Feature Rotation Invariance Learning for Point Cloud Analysis

Feature Rotation Invariance Learning for Point Cloud Analysi...

引用

Smart World Congress (SWC), IEEE

作者： Lu Shi Qi Cao Guoqing Zhang Jin Yi Yansen Huang Yigang Cen State Key Laboratory of Advanced Rail Autonomous Operation the School of Computer Science and Technology and Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China the School of Computing Science University of Glasgow Singapore With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education the State Key Laboratory of Advanced Rail Autonomous Operation and the School of Computer and Information Technology Beijing Jiaotong University Beijing China the College of Civil Engineering Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. LTD Guizhou China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks.

关键词： Point cloud compression Representation learning Analytical models Solid modeling Visualization Three-dimensional displays Semantics Cloning Feature extraction data models

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：