检索结果-内蒙古大学图书馆

2019 International Conference on Robotics Systems and Vehicle Technology, RSVT 2019

作者： Tang, Xuetao Zhu, Yi Hu, Xuegang Li, Peipei Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China

ISBN: (纸本)9781450362429

The excellent performance of short texts classification has emerged in the past few years. However, massive short texts with few words like invoice data are different with traditional short texts like tweets in its no contextual and less semantic information, which hinders the application of conventional classification algorithms. To address these problems, we propose an integrated classification model for massive short texts with few words. More specifically, the word embedding model is introduced to train the word vectors of massive short texts with few words to form the feature space, and then the vector representation of each instance in texts is trained based on sentence embedding. With this integrated model, higher level representations are learned from massive short texts with few words. It can boost the performance of the base subsequent classifiers such as K-Nearest Neighbor. Extensive experiments conducted on dataset including 16 million real data demonstrate the superior classification performance of our proposed model compared with all competing state-of-the-art models. © 2019 Association for Computing Machinery.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

XCoref: Cross-document coreference resolution in the wild

arXiv

引用

arXiv 2021年

作者： Zhukova, Anastasia Hamborg, Felix Donnay, Karsten Gipp, Bela Data and Knowledge Engineering University of Wuppertal Germany Dept. of Computer Science University of Konstanz Germany Dept. of Political Science University of Zurich Switzerland Heidelberg Academy of Sciences and Humanities Germany

datasets and methods for cross-document coreference resolution (CDCR) focus on events or entities with strict coreference relations. They lack, however, annotating and resolving coreference mentions with more abstract or loose relations that may occur when news articles report about controversial and polarized events. Bridging and loose coreference relations trigger associations that may lead to exposing news readers to bias by word choice and labeling. For example, coreferential mentions of "direct talks between U.S. President Donald Trump and Kim" such as "an extraordinary meeting following months of heated rhetoric" or "great chance to solve a world problem" form a more positive perception of this event. A step towards bringing awareness of bias by word choice and labeling is the reliable resolution of coreferences with high lexical diversity. We propose an unsupervised method named XCoref, which is a CDCR method that capably resolves not only previously prevalent entities, such as persons, e.g., "Donald Trump," but also abstractly defined concepts, such as groups of persons, "caravan of immigrants," events and actions, e.g., "marching to the U.S. border." In an extensive evaluation, we compare the proposed XCoref to a state-of-the-art CDCR method and a previous method TCA that resolves such complex coreference relations and find that XCoref outperforms these methods. Outperforming an established CDCR model shows that the new CDCR models need to be evaluated on semantically complex mentions with more loose coreference relations to indicate their applicability of models to resolve mentions in the "wild" of political news articles. © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In-memory join algorithms on GPUs for large-data 21

In-memory join algorithms on GPUs for large-data

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Guo, Chengxin Chen, Hong Key Lab of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renmin University of China Beijing China

ISBN: (纸本)9781728120584

In traditional databases, join is one of the most computationally expensive operations in query processing. During the past years, GPU has been adopted to improve the performance of join processing because of the features of massive parallelism and high memory bandwidth. Limited by the capacity of GPU memory and the absence of virtual memory management, however, handling the relations that exceed the capacity of the GPU memory is a challenge for GPU-based join algorithms. Because of the high computing throughput provided by GPUs and the low bandwidth of data communication between the CPUs and the GPUs, data have to be partitioned to fit the features of GPUs and to reduce the cost of data transmission. Furthermore, a series of novel techniques have been developed on the GPUs, which can benefit the join algorithms. In this work, we focus on the optimizing of processing join operator on large relations and propose the designs of in-memory hash join and sort-merge join on GPUs. We present the data partition method on the GPUs implemented with a pipeline mechanism. Furthermore, the shuffle instructions and the CUDA streams are applied in our algorithms to best utilize the GPUs. Experimental results indicate that our hash join algorithm delivers up to 1.51X and 1.24X speedup over the state-of-the-art hash join algorithm on CPUs on NVIDIA GTX1080ti-Pascal GPU and TitanV-Volta GPU respectively. For sort-merge join, our algorithm achieves up to 3.52X and 2.21X improvements on the same GPUs respectively compared to the baselines on CPUs. © 2019 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Parallel hybrid join algorithm on GPU 21

Parallel hybrid join algorithm on GPU

引用

作者： Guo, Chengxin Chen, Hong Zhang, Feng Li, Cuiping Key Lab of Data Engineering and Knowledge Engineering Ministry of Education School of Information Renmin University of China Beijing China

ISBN: (纸本)9781728120584

In data analytics applications, join is a general and time consuming operation. Optimizing join algorithms can benefit the query processing significantly. The emerging of GPUs provides a massive parallelism solution for improving the performance of the join operation. The hash join (HJ) and sort merge join (SMJ), which are two widely used join algorithms, have been proved effective for efficient join processing on the GPUs. Both algorithms have their own advantages and drawbacks, offering the chance of combining the advantages of HJ and SMJ on GPUs. In processing join operation on GPUs, data need to be transmitted between the CPU and the GPU due to the discrete GPU memory design, which causes performance degradation because of the high PCIe data transfer overhead. As GPUs are becoming more powerful than before, the performance gap between data transmission and GPU execution increases, which makes it even harder to implement an efficient join on GPUs. In this paper, we focus on the optimization of join algorithms on GPUs. We propose the Parallel Hybrid Join algorithm on GPUs(PHYJ) to combine the advantages of HJ and SMJ, and overlap the data communication and GPU execution with a pipeline mechanism. In our evaluation, the PHYJ shows up to 1.72X and 1.55X speedup over the up-to-date HJ and SMJ algorithms respectively on a NVIDIA GTX 1080ti-Pascal GPU. On the TitanV-Volta GPU, up to 1.54X and 1.42X improvements can be achieved over the baseline HJ and SMJ algorithms respectively. © 2019 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

data Augmentation Approach for Language Identification in Imbalanced Bilingual Code-Mixed Social Media datasets

Data Augmentation Approach for Language Identification in Im...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Mohd Suhairi Md Suhaimin Mohd Hanafi Ahmad Hijazi Ervin Gubin Moung Mohd Azwan Mohamad Hamza Data Technology and Applications Research Group Faculty of Computing and Informatics Universiti Malaysia Sabah Sabah Malaysia Polytechnic and Community College Education Department Ministry of Higher Education Malaysia Putrajaya Malaysia Faculty of Computing and Informatics Creative Advanced Machine Intelligence Research Centre Universiti Malaysia Sabah Sabah Malaysia Knowledge Engineering & Computational Linguistic (KECL) Research Group Universiti Malaysia Pahang Pahang Malaysia

Addressing the problem of language identification in code-mixed datasets poses notable challenges due to data scarcity and high confusability in bilingual contexts. These challenges are further amplified by the associated imbalance and noise characteristic of social media data, complicating efforts to optimize performance. This paper introduces an augmentation approach designed to enhance language identification in bilingual code-mixed social media data. By incorporating reverse translation, semantic similarity, and sampling techniques alongside customized reprocessing strategies, our approach offers a comprehensive solution to these complex issues. To evaluate the effectiveness of the proposed approach, experiments were conducted on language identification at both the sentence and word levels. The results demonstrated the potential of the approach in optimizing language identification performance, offering a compelling combination of generation techniques for addressing the challenges of language identification in code-mixed data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

Generating Action-conditioned Prompts for Open-vocabulary Vi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Neuroinformatics, Neural Networks and Neurocomputers for Brain-inspired Computational Intelligence

Neuroinformatics, Neural Networks and Neurocomputers for Bra...

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Nikola K Kasabov Fellow INNS College of Fellows Fellow RSNZ Doctor Honoris Causa Obuda University Budapest Founding Director KEDRI and Knowledge Engineering Auckland University of Technology Auckland New Zealand George Moore Chair Data Analytics Ulster University Derry the UK Visiting Professor IICT Bulgarian Academy of Sciences Sofia BG Honorary Professor Teesside University UK The University of Auckland NZ Peking University Shenzhen

The talk discusses briefly current challenges in artificial intelligence (AI), including: efficient learning of data (interactive, adaptive, life-long; transfer); interpretability and explainability; personalised predictive modelling and profiling; multiple modality of data (e.g. genetic, clinical, behaviour, cognitive, static, temporal, longitudinal); computational complexity; energy consumption; human-machine interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Marginal energy consumption cost factors of battery electric buses

Marginal energy consumption cost factors of battery electric...

引用

Smart Cities Symposium Prague (SCSP)

作者： Pé ter Á kos Szilassy Bence Jenő fi Dá vid Fö ldes PhD Student BME-KTKG and Transport Engineer NATUK Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Hungary Hungarian National Data Economy Knowledge Centre (Neumann J&#x00E1 nos Nonprofit Ltd. - NATUK) Budapest Business Analyst NATUK nos Nonprofit Ltd. - NATUK) Budapest Hungary Research Associate BME-KTKG Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Budapest Hungary

Regulatory environment in the EU already mandates public transport providers (PTP) to detail their cost accounting to the level of each line they operate. Models used, however, fail to utilise the level of precision state of the art technology would allow for; therefore, state-owned providers become uncompetitive. Implementing new technologies such as electric buses have high investment costs; thus, reconsidering the cost structure of an operator is essential. The aim of this paper is to introduce an innovative cost calculation method for battery electric bus operation. The novelty of the model is its foundation on telemetric data generated by sensors hosted in electric buses and the consequent use of marginal consumption costs instead of averages based on aggregations. The model introduced focuses on the cost of energy consumption, examines influencing factors, such as the effect of meteorological externalities on auxiliary systems, and considers driving dynamics. Nonetheless, fix costs such as amortisation and labour costs are also accounted for to give a complete picture of per passenger numbers. The model developed was applied as a case study to prove its applicability. We found that the climbed elevation positively correlates, while the number of stops served at a given distance negatively correlates with the increase in consumption. The model is better suited for improving the operative competitiveness of PTPs rather than as a tool for regulatory compliance.

关键词： Energy consumption Costs Smart cities Biological system modeling Roads Batteries Sensors

来源：评论

学校读者我要写书评

暂无评论

Towards Target-dependent Sentiment Classification in News Articles

arXiv

引用

arXiv 2021年

作者： Donnay, Karsten Gipp, Bela Hamborg, Felix Dept. of Computer Science University of Konstanz Germany Heidelberg Academy of Sciences and Humanities Germany Dept. of Political Science University of Zurich Switzerland Data and Knowledge Engineering University of Wuppertal Germany

Extensive research on target-dependent sentiment classification (TSC) has led to strong classification performances in domains where authors tend to explicitly express sentiment about specific entities or topics, such as in reviews or on social media. We investigate TSC in news articles, a much less researched domain, despite the importance of news as an essential information source in individual and societal decision making. This article introduces NewsTSC, a manually annotated dataset to explore TSC on news articles. Investigating characteristics of sentiment in news and contrasting them to popular TSC domains, we find that sentiment in the news is expressed less explicitly, is more dependent on context and readership, and requires a greater degree of interpretation. In an extensive evaluation, we find that the current state-of-the-art in TSC performs worse on news articles than on other domains (average recall AvgRec = 69.8 on NewsTSC compared to AvgRev = [75.6, 82.2] on established TSC datasets). Reasons include incorrectly resolved relation of target and sentiment-bearing phrases and off-context dependence. As a major improvement over previous news TSC, we find that BERT’s natural language understanding capabilities capture the less explicit sentiment used in news articles. © 2021, CC BY-SA.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition

arXiv

引用

arXiv 2023年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo School of Computer Science and Technology The Ministry of Education Key Laboratory for Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong Shaanxi Xi’an710049 China School of Computer Science and Technology Xi’an Jiaotong Shaanxi Xi’an710049 China The BigKE Joint Innovation Center SHMEEA Shanghai China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. Copyright © 2023, 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：