检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ma, Jie Wang, Pinghui Kong, Dechen Wang, Zewei Liu, Jun Pei, Hongbin Zhao, Junzhou Di, Jia The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Automation Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Thirdly, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Land degradation sensitivity assessment and convergence analysis in Korla of Xinjiang, China

引用

Journal of Arid Land 2020年第4期12卷 594-608页

作者： DING Jinchen CHEN Yunzhi WANG Xiaoqin CAO Meiqin Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education National&Local Joint Engineering Research Center of Satellite Geospatial Information TechnologyFuzhou UniversityFuzhou 350108China

Land degradation has a major impact on environmental and socio-economic sustainability. Scientific methods are necessary to monitor the risk of land degradation. In this study, the environmental sensitive area index(ESAI) was utilized to assess land degradation sensitivity and convergence analysis in Korla, a typical oasis city in Xinjiang of China, which is located on the northeast border of the Tarim Basin. A total of 18 indicators depicting soil, climate, vegetation, and management qualities were used to illustrate spatial-temporal patterns of land degradation sensitivity from 1994 to 2018. We investigated the causes of spatial convergence and divergence based on the Ordinary Least Squares(OLS) and Geographically Weighted Regression(GWR) models. The results show that the branch of the Tianshan Mountains and oasis plain had a low sensitivity to land degradation, while the Tarim Basin had a high risk of land degradation. More than two-thirds of the study area can be categorized as "critical" sensitivity classes. The largest percentage(32.6%) of fragile classes was observed for 2006. There was no significant change in insensitive or low-sensitivity areas, which accounted for less than 0.4% of the entire observation period. The ESAI of the four time periods(1994–1998, 1998–2006, 2006–2010, and 2010–2018) formed a series of convergence patterns. The convergence patterns of 1994–1998 and 1998–2006 can be explained by the government's efforts to "Returning Farmland to Forests" and other governance projects. In 2006–2010, the construction of afforested work intensified, but industrial development and human activities affected the convergence pattern. The pattern of convergence in most regions between 2010 and 2018 can be attributed to the government's implementation of a series of key ecological protection projects, which led to a decrease in sensitivity to land degradation. The results of this study altogether suggest that the ESAI convergence analysis is an effective e

关键词： land degradation quality index convergence analysis remote sensing environmental sensitive area index Korla

来源：评论

学校读者我要写书评

暂无评论

Tight upper bound of the maximal quantum violation of Gisin’s elegant Bell inequality and its application in randomness certification

arXiv

引用

arXiv 2024年

作者： Hu, Dan-Dan Li, Meng-Yan Guo, Fen-Zhuo Wang, Yu-Kun Dong, Hai-Feng Gao, Fei School of Science Beijing University of Posts and Telecommunications Beijing100876 China Henan Key Laboratory of Network Cryptography Technology Zhengzhou450001 China Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum-Beijing Beijing102249 China School of Instrumentation Science and Opto-Electronics Engineering Beihang University Beijing100191 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

The violation of a Bell inequality implies the existence of nonlocality, making device-independent randomness certification possible. This paper derives a tight upper bound for the maximal quantum violation of Gisin’s elegant Bell inequality (EBI) for arbitrary two-qubit states, along with the constraints required to achieve this bound. This method provides the necessary and sufficient conditions for violating the EBI for several quantum states, including pure two-qubit states and the Werner states. The lower bound of certifiable global randomness is analyzed based on the tight upper bound of the EBI for pure two-qubit states, with a comparison to the Clauser-Horne-Shimony-Holt (CHSH) inequality. The relationship between the noise level and the lower bound of certifiable global randomness with respect to the Werner states is also explored, and the comparisons with both the CHSH inequality and the chained inequality are given. The results indicate that when the state approaches a maximally entangled state within specific quantified ranges, the EBI demonstrates advantages over both the CHSH inequality and the chained inequality, potentially enhancing practical device-independent randomness generation rates. Copyright © 2024, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Impact of China Railway Express on Urban Exports: Evidence from Prefectural-Level City Economic data 9th

Impact of China Railway Express on Urban Exports: Evidence f...

引用

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Yan, Bochao Tian, Xin Deng, Shiyong Wu, Junfeng Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China China Railway Fifth Survey and Design Institute Group Co. Ltd. Beijing102600 China Shanghai WinJoin Information Technology Co. Ltd. Shanghai200126 China

As a key project of infrastructure connectivity in the "Five-Pronged Approach"of strategic construction "The Belt and Road", the China Railway Express, has significantly improved the level of trade level in countries along the railway. This study uses an empirical model to correlate the container export data of China Railway Express from June 2020 to June 2021 with the export value and finds that the trade volume of China Railway Express is positively correlated with the export value of cities. The relationship between the operation of the China Railway Express and the export trade of cities that enjoy the rail service is rigorously explained through the actual data of the operation of the China Railway Express provided by the enterprises. The empirical results further prove the positive impact of the China Railway Express on cities that enjoy the rail service. © 2022 The Authors. Published by Elsevier B.V.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Generative Aspect Based Sentiment Analysis for Online Health Community with data Augmentation

SSRN

引用

SSRN 2023年

作者： Han, Pu Ye, Dongyu Gu, Liang Chen, Wenqi Wei, Hongchen Li, Xiaoyan School of Management Nanjing University of Posts & Telecommunications Nanjing210003 China Jiangsu Provincial Key Laboratory of Data Engineering and Knowledge Service Nanjing210023 China School of Basic Medical Sciences Nanjing Medical University Nanjing210029 China

Accurate analysis of patients' feedback on various medical aspects is of great importance for improving the quality of healthcare services. In this paper, we address the task of extracting aspects and opinions by adopting a generative end-to-end deep learning model. And we address the challenge of limited high-quality labeled data in aspect-based sentiment analysis by introducing a data augmentation method. To evaluate the effectiveness of our proposed generative model and data augmentation technique in the healthcare domain, we collected reviews related to diagnosis and treatment from online health communities(OHC) and verified the effectiveness of the proposed model. The experimental results demonstrate the superiority of generative models in complex aspect-based sentiment analysis tasks. Furthermore, we find that our data augmentation method is effective in enhancing the experimental outcomes. Our work contributes to the advancement of natural language processing techniques in the healthcare domain, and it has the potential to improve the quality of healthcare services through more fine-grained analysis of patients' feedback. © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Discovering the relationship between the number of film review topics and box office with NLP techniques 11

Discovering the relationship between the number of film revi...

引用

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Li, Bo Dai, Wei Liu, Shang Shi, Yong School of Finance and Economics Wuhan City Vocational College No. 10 Yezhihu West Road Hongshan District Wuhan430064 China PKU-WUHAN Institute for Artificial Intelligence No. 770 Gaoxin Avenue Hongshan District Wuhan430070 China School of Economics Shanghai University 99 Shangda Road BaoShan District Shanghai200444 China School of Economics and Management University of Chinese Academy of Sciences No. 3 Zhongguancun South Yitiao Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences No. 80 Zhongguancun East Road Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences No. 80 Zhongguancun East Road Beijing100190 China

Numerous movie reviews on the internet can be used to analyze audience experiences of movies and provide inspiration for the operation and production of movies. In this work, we integrate and match the review data on Douban and the box office data on the website ***, and utilize the topic model in natural language processing to determine the number of each movie review topics, then establish an regression equation to analyze the relationship between the number of topics and movie box office. Our analysis shows a significant positive correlation between film box office and the number of movie review topics, and we have provided an explanation for this. Finally, we also analyzed the practical application value of this work. © 2024 The Authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Impact of Consumer Characteristics on IP Product Purchase: Empirical Evidence from a Chinese Chain Retailer 10

Impact of Consumer Characteristics on IP Product Purchase: E...

引用

10th International Conference on Information Technology and Quantitative Management, ITQM 2023

作者： Tang, Jiayu Wang, Tingyan Tian, Xin Cai, Qiang Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China Sino-Danish College University of Chinese Academy of Sciences Beijing100190 China Nuffield Department of Medicine University of Oxford South Parks Road OxfordOX1 3SY United Kingdom NIHR Oxford Biomedical Research Centre Big Data Institute University of Oxford Old Road Campus OxfordOX3 7LF United Kingdom School of Economics and Management Ningbo University of Technology Ningbo315211 China

Developing IP product has become a common differentiation strategy for retailers to attract customers and remain competence strength. This study uses empirical model to relate consumer characteristics with IP product purchase. The results show that consumers shopping on weekends are more likely to buy IP products, and consumers who have stocking behavior are less likely to purchase IP products. Consumers who are members of the retailer also have lower probability to buy IP products. These findings provide suggestions for the retailers who want to apply differentiation strategy by introducing co-branded IP products. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative Management.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction

arXiv

引用

arXiv 2023年

作者： Wan, Qizhi Wan, Changxuan Xiao, Keli Xiong, Hui Liu, Dexi Liu, Xiping Jiangxi Key Laboratory of Data and Knowledge Engineering China School of Information Management Jiangxi University of Finance and Economics Jiangxi Nanchang China College of Business Stony Brook University Stony BrookNY United States Guangdong Guangzhou China

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the problem as multiple learning tasks leads to increased model complexity. Also, existing methods insufficiently utilize the correlation of entities crossing different events, resulting in limited event extraction performance. This paper introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role and a multi-channel argument role prediction module. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. By leveraging the multichannel prediction module, we transform entity and multi-event extraction into a single task of predicting token-event pairs, thereby reducing the overall parameter size and enhancing model efficiency. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F1 score, highlighting its superior performance in event extraction. Furthermore, an ablation study confirms the significant value of the proposed data structure in improving event extraction tasks, further validating its importance in enhancing the overall performance of the framework. Copyright © 2023, The Authors. All rights reserved.

关键词： data structures

来源：评论

学校读者我要写书评

暂无评论

Generative Aspect Based Sentiment Analysis for Online Health Community with data Augmentation

SSRN

引用

SSRN 2023年

Accurate analysis of patients' feedback on various medical aspects is of great importance for improving the quality of healthcare services. In this paper, we address the task of extracting aspects and opinions by adopting a generative end-to-end deep learning model. And we address the challenge of limited high-quality labeled data in aspect-based sentiment analysis by introducing a data augmentation method. To evaluate the effectiveness of our proposed generative model and data augmentation technique in the healthcare domain, we collected reviews related to diagnosis and treatment from online health communities(OHC) and verified the effectiveness of the proposed model. The experimental results demonstrate the superiority of generative models in complex aspect-based sentiment analysis tasks, showing a noteworthy nearly 13% increase in F1 score. Furthermore, we find that our data augmentation method is effective in enhancing the experimental outcomes. Our work contributes to the advancement of natural language processing techniques in the healthcare domain, and it has the potential to improve the quality of healthcare services through more fine-grained analysis of patients' feedback. Our code and dataset are available at https://***/woloc/OHC_*** now. © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Emotion-Cause Pair Extraction Based on knowledge-Transfer 21

Emotion-Cause Pair Extraction Based on Knowledge-Transfer

引用

21st Chinese National Conference on Computational Linguistic, CCL 2022

作者： Fengyuan, Zhao Dexi, Liu Qizhi, Wan Changxuan, Wan Xiping, Liu Guoqiong, Liao School of Information Management Jiangxi University of Finance and Economics Jiangxi Nanchang China Jiangxi University of Finance and Economics Key Laboratory of Data and Knowledge Engineering Jiangxi Nanchang China

The existing emotion cause pair extraction models do not improve the performance of emotion cause pair extraction by incorporating external knowledge. In this work, we propose an emotion-cause pair extraction model based on knowledge transfer (ECPE-KT), in which knowledge is utilized to obtain explicit knowledge encoding of text. Subsequently, the implicit knowledge encoding of clauses is obtained by the transfer of external sentiment classification corpus. Moreover, conduct filtering via adding the relative position and prediction probability to the representation of clause semantic features. Transformer with window mechanism is used to optimize the calculation pressure. Experimental results show that the proposed method outperforms the state-of-the-art method, i.e., ECPE-2D. © 2022 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License.

关键词： Extraction

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：