检索结果-内蒙古大学图书馆

A Multi-semantics Classification Method Based on Deep Learning for Incredible Messages on social Media

Chinese Journal of Electronics 2019年第4期28卷 754-763页

作者： WU Lianwei RAO Yuan YU Hualei WANG Yiming AMBREEN Nazir Lab of Social Intelligence and Complex Data Processing School of Software Engineering Xi'an Jiaotong University

How to classify incredible messages has attracted great attention from academic and industry nowadays. The recent work mainly focuses on one type of incredible messages(a.k.a rumors or fake news) and achieves some success to detect them. The existing problem is that incredible messages have different types on social media, and rumors or fake news cannot represent all incredible messages. Based on this, in the paper, we divide messages on social media into five types based on three dimensions of information evaluation metrics. And a novel method is proposed based on deep learning for classifying the five types of incredible messages on social *** specifically, we use attention mechanism to obtain deep text semantic features and strengthen emotional semantics features, meanwhile, construct universal metadata as auxiliary features, concatenating them for incredible messages classification. A series of experiments on two representative real-world datasets demonstrate that the proposed method outperforms the state-of-the-art methods.

关键词： Information credibility evaluation Rumor detection social media Text classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid Siamese Masked Autoencoders as Unsupervised Video Summarizer

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Xu, Yifei Wu, Zaiqiang Li, Li Li, Siqi Li, Wenlong Li, Mingqi Rao, Yuan Deng, Shuiguang Xi’an Jiao-tong University School of Software Shaanxi Xi’an710054 China Xi’an Jiaotong University Suzhou Institute Jiangsu Suzhou215000 China Shaanxi Joint Key Laboratory for Artifact Intelligence Shaanxi Xi’an710054 China Xi’an Key Laboratory for Social Intelligence and Complex Data Processing Shaanxi Xi’an710054 China Alltuu Inc Zhejiang Hangzhou310000 China College of Computer Science and Technology in Zhejiang University Zhejiang Hangzhou310027 China

Video summarization aims to seek the most important information from a source video while still retaining its primary content. In practical application, unsupervised video summarizers are acknowledged for their flexibility and superiority without requiring annotated data. However, they are looking for the determined rules on how much each frame is essential enough to be selected as a summary. Unlike conventional frame-based scoring methods, we propose a shot-level unsupervised video summarizer termed Hybrid Siamese Masked Autoencoders (H-SMAE) from a higher semantic perspective. Specifically, our method consists of Multi-view Siamese Masked Autoencoders (MV-SMAE) and Shot Diversity Enhancer (SDE). MV-SMAE tries to recover the masked shots from original frame feature and three unmasked shot subsets with elaborate Siamese masked autoencoders. Inspired by the masking idea in MAE, MV-SMAE introduces a Siamese architecture to model prior references to guide the reconstruction of masked shots. Besides, SDE improves the diversity of generated summary by minimizing the repelling loss among selected shots. Afterward, these two modules are fused followed by 0-1 knapsack algorithm to produce a video summary. Experiments on two challenging and diverse datasets demonstrate that our approach outperforms other state-of- the-art unsupervised and weakly-supervised methods, and even generates comparable results with several excellent supervised methods. The source code of H-SMAE is available at https://***/wzq0214/H-SMAE. © 1991-2012 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A method of Chinese named entity recognition based on CNN-BILSTM-CRF model 1

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Long, Sun Yuan, Rao Yi, Lu Xue, Li Lab of Social Intelligence & Complex Data Processing School of Software Xi’an Jiaotong University Xi’an710049 China

ISBN: (数字)9789811322068

ISBN: (纸本)9789811322051

The main task of naming entity recognition is to identify the person names, location names, organization names, meaningful time, dates and other quantitative phrases and also classifying them into different categories. Yet, there are lots of field terms, meaningful entities, complicated location names and complex name of organizations contained in all kinds of these field terms is the most important mission in digging out the text now. The extraction of Chinese is more difficult than English entities owing to the lack of definite boundary and size characteristics of Chinese words. Therefore, we would train and test the marked corpus which is based on the CNN-BILSTM-CRF neutral network model in order to make good use of CNN to get the presentation character of words and label the words by using BILSTM and CRF. It makes the extraction of entity in the common came true. The experimental results show that the accuracy rate, recall rate and F value that we got in an unaddressed artificial features condition are 98.81%, 90.70% and 91.57% respectively which is better than the results we got by using the method of BILSTM+CRF and conditional random field (CRF). © Springer Nature Singapore Pte Ltd. 2018.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research progress of knowledge graph based on knowledge base embedding 1

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Caifang, Tang Yuan, Rao Hualei, Yu Jiamin, Cheng Lab of Social Intelligence & Complex Data Processing School of Software Xi’an Jiaotong University Xi’an710049 China

ISBN: (数字)9789811322068

ISBN: (纸本)9789811322051

The knowledge Graph (KGs) is a valuable tool and useful resource to describe the entities and their relationships in various natural language processing tasks. Especially, the insufficient semantic of entities and relationship in text limited the efficiency and accuracy of knowledge representation. With the increasing of knowledge base resources, many scholars began to study the knowledge graph’s construction technology based on knowledge base embedding. The basic idea is that the knowledge graph will be treated as a recursive process. Through utilizing the knowledge base’s resources and the semantic representation of text characteristic, we can extend the new features that improve learning performance and knowledge graph completeness. In this paper, we give a general overview of knowledge graph’s construction research based on knowledge embedding, including knowledge representation, knowledge embedding and so on. Then we summarize the challenge for the knowledge graph and the future development trend. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Relation Extraction Based on Dual Attention Mechanism 5th

Relation Extraction Based on Dual Attention Mechanism

引用

5th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2019

作者： Li, Xue Rao, Yuan Sun, Long Lu, Yi Lab of Social Intelligence and Complex Data Processing School of Software Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9789811501173

The traditional deep learning model has problems that the long-distance dependent information cannot be learned, and the correlation between the input and output of the model is not considered. And the information processing on the sentence set is still insufficient. Aiming at the above problems, a relation extraction method combining bidirectional GRU network and multi-attention mechanism is proposed. The word-level attention mechanism was used to extract the word-level features from the sentence, and the sentence-level attention mechanism was used to focus on the characteristics of sentence sets. The experimental verification in the NYT dataset was conducted. The experimental results show that the proposed method can effectively improve the F1 value of the relationship extraction. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Enhancement and Multi-level label Embedding for Chinese News Headline Classification 14

Semantic Enhancement and Multi-level Label Embedding for Chi...

引用

14th International Joint Symposium on Artificial intelligence and Natural Language processing, iSAI-NLP 2019

作者： Qi, Jiangnan Rao, Yuan Sun, Ling Yang, Xiong School of Software Engineering xi'An Jiao Tong University Lab of Social Intelligence and Complex Data Processing Xi'an China

ISBN: (纸本)9781728156316

News headline classification is a specific example of short text classification, which aims to extract semantic information from the short text and classify it accurately. It can provide a fast classification method for data of various kinds of news media, thus arousing the common concern of academia and industry. Most short text classification methods are based on the semantic expansion of external knowledge, which is unable to expansion dynamically in real time and make full use of label information. To overcome these problems, we propose a novel method which consists of three parts: semantic enhancement, multi-dimensional feature fusion network and multi-level label embedding. Firstly, the word-level semantic information are embedded into the character encoding from pre-Train model to enhance semantic features. Secondly, both of Bi-GRU and multi-scale CNN are used to extract sequence and local features of text to enhance the semantic representation of the sentence. Furthermore, the multi-level label embedding is used to filter textual vector and assist classification in the word and sentence level respectively. Experimental results on NLPCC 2017 Chinese news headline classification task show that our model achieves 84.74% of accuracy and 84.75% of F1, improves over the best baseline model by 1.5% and 1.6%, respectively, and reaches the state-of-The-Art performance. © 2019 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Fighting False Information from Propagation Process: A Survey

引用

ACM COMPUTING SURVEYS 2023年第10期55卷 1-38页

作者： Sun, Ling Rao, Yuan Wu, Lianwei Zhang, Xiangbo Lan, Yuqian Nazir, Ambreen Xi An Jiao Tong Univ Sch Software Engn Xian Key Lab Social Intelligence & Complex Data P Xian 710049 Shaanxi Peoples R China

The recent serious cases of spreading false information have posed a significant threat to the social stability and even national security, urgently requiring all circles to respond adequately. Therefore, this survey illustrates how to fight against false information from its propagation process by (1) exploring the drivers of information infectivity from the content, media, user, structural, and temporal dimensions;(2) describing the propagation modeling approaches from macro (global), meso (community), and micro (individual) levels;and (3) discussing the governance strategies from both technical and application aspects. The potential data sources and the future directions of fighting are also given, hoping to facilitate more comprehensive solutions.

关键词： False information socialmedia information infectivity propagation modeling propagation governance

来源：评论

学校读者我要写书评

暂无评论

Research on News Topic-driven Market Flucatuation and Predication

Research on News Topic-driven Market Flucatuation and Predic...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Rao, Yuan Zhong, Xuhui Lu, Shumin Xi An Jiao Tong Univ Sch Software Engn Lab Social Intelligence & Complex Data Proc Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Humanity Social Sci Lab Social Intelligence & Complex Data Proc Xian 710049 Peoples R China

ISBN: (纸本)9781509059522

In order to forecast the price movement of stock with the correlated news events, an enhanced Topic-driven model with the positional weight of feature words and label of stocks, named LP-LDA model, is proposed to represent and analyze the intrinsic mechanism in financial market. The experiment results show that LP-LDA has a better performance than traditional LDA model. Especially, when the number of topics are increasing, the running time of LP-LDA model are 0.69s, 0.78 s and 1.15s at 100, 200 and 300 topics, respectively, which are better than LDA. Furthermore, Degree of Influence (DoI) is defined to describe the considerable influence about the news events on the price movement of certain stock, which provides a new mechanism to measure the fluctuating price. The experiment results shown that the coefficient of correlation between news topic and return rate of stock is 0.9137, which is much higher than other results of experiment.

关键词： News Topic Recognition LP-based LDA Degree of Influence Price Movement

来源：评论

学校读者我要写书评

暂无评论

social Network-based Stock Correlation Analysis and Prediction

Social Network-based Stock Correlation Analysis and Predicti...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Rao, Yuan Zhong, Xuhui Lu, Shumin Xi An Jiao Tong Univ Sch Software Engn Lab Social Intelligence & Complex Data Proc Xian 710049 Peoples R China Xi An Jiao Tong Univ Lab Social Intelligence & Complex Data Proc Sch Humanity Social Sci Xian 710049 Peoples R China

ISBN: (纸本)9781509059522

In order to forecast the price movement with the correlation between two different stocks, the model of Stock social Network (SSN) is proposed to represent and analyze the intrinsic complex relationship. We choose 313 stocks from 9 industries to build an evolution model of SSN, which predicted that some stocks clusters are isolated and the nodes and edges in SSN are decreasing distinctly step by step with the change of threshold delta from 0.7, 0.75 and 0.8, respectively. Meanwhile, the coverage rate of nodes in SSN arrives 0.2076 at delta = 0.8, in reverse, the 79.24% nodes is trimmed during the process of evolution of SSN. Based on these results, we design a new portfolio strategy based on new index, named CSSNI, to optimize the asset pricing model. The results show that the ratio of return is 0.92666 based on the CSSNI, which is much better than the result by traditional strategy.

关键词： Stock social network Price Movement Forecasting Risk of Stock Asset Portfolio

来源：评论

学校读者我要写书评

暂无评论

Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection 9

Different Absorption from the Same Sharing: Sifted Multi-tas...

引用

Conference on Empirical Methods in Natural Language processing / 9th International Joint Conference on Natural Language processing (EMNLP-IJCNLP)

作者： Wu, Lianwei Rao, Yuan Jin, Haolin Nazir, Ambreen Sun, Ling Xi An Jiao Tong Univ Sch Software Engn Lab Social Intelligence & Complex Data Proc Xian 710049 Peoples R China

ISBN: (纸本)9781950737901

Recently, neural networks based on multi-task learning have achieved promising performance on fake news detection, which focus on learning shared features among tasks as complementary features to serve different tasks. However, in most of the existing approaches, the shared features are completely assigned to different tasks without selection, which may lead to some useless and even adverse features integrated into specific tasks. In this paper, we design a sifted multi-task learning method with a selected sharing layer for fake news detection. The selected sharing layer adopts gate mechanism and attention mechanism to filter and select shared feature flows between tasks. Experiments on two public and widely used competition datasets, i.e. RumourEval and PHEME, demonstrate that our proposed method achieves the state-of-the-art performance and boosts the F1-score by more than 0.87%, 1.31%, respectively.

关键词： Learning systems

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：