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

Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning

引用

Chinese Journal of Electronics 2021年第4期30卷 623-633页

作者： TANG Caifang RAO Yuan YU Hualei SUN Ling CHENG Jiamin WANG Yutian Xi'an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software EngineeringXi'an Jiaotong University Shaanxi Joint Key Laboratory for Artifact Intelligence School of Software EngineeringXi'an Jiaotong University School of Software Engineering Xi'an Jiaotong University

Knowledge graph is a useful resources and tools for describing entities and relationships in natural language processing tasks. However, the existing knowledge graph are incomplete. Therefore, knowledge graph completion technology has become a research hotspot in the field of artificial intelligence, but the traditional knowledge graph embedding method does not fully take into account the role of logic rules and the effect of false negative samples on knowledge *** on the logic rules of knowledge and the role of adversarial learning in knowledge embedding, we proposes a model to improve the completion of knowledge graph:soft Rules and graph adversarial learning(RUGA). Firstly,the traditional knowledge graph embedding model is trained as generator and discriminator by using adversarial learning method, and high-quality negative samples are obtained. Then these negative samples and the existing positive samples together constitute the label triple in the injection rule model. The whole model will benefit from both high-quality samples and logical rules. In addition,we evaluated the performance of link prediction task and triple classification task on Freebase and Yago datasets respectively. Finally, the experimental results show that the model can effectively improve the effect of knowledge graph completion.

关键词： Knowledge graph Knowledge embedding Knowledge graph completion Adversarial learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Unsupervised Text Style Transfer Based on Deep Learning 4

A Review of Unsupervised Text Style Transfer Based on Deep L...

引用

4th International Conference on Artificial intelligence and Electromechanical Automation, AIEA 2023

作者： Guo, Zicheng Rao, Yuan Xi'an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China

ISBN: (纸本)9781510666412

Text style transfer is mainly to modify the text style to suit various application scenarios without changing the semantic meaning of the text, which is a great significant issue in natural language processing. To expedite research progress, this survey conducts a systematic review of existing literature. Drawing from a vast body of research, this survey first extracts the essential connotations of style information in text of varying granularity across different tasks, and then provide a clear definition of text style transfer, summarize the main challenges at present and comprehensively codify and discuss the current datasets used for evaluation, as well as their indicators. Moreover, this survey compares the mechanisms, advantages, and shortcomings of unsupervised classical methods across word, sentence, and paragraph levels. Finally, the future directions of fighting are also given, hoping to facilitate more comprehensive solutions. © 2023 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evidence-aware hierarchical interactive attention networks for explainable claim verification 29

Evidence-aware hierarchical interactive attention networks f...

引用

29th International Joint Conference on Artificial intelligence, IJCAI 2020

作者： Wu, Lianwei Rao, Yuan Yang, Xiong Wang, Wanzhen Nazir, Ambreen Lab of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University China Shannxi Joint Key Laboratory for Artifact Intelligence Sub-Lab of Xi'an Jiaotong University China Research Institute of Xi'an Jiaotong University Shenzhen China

ISBN: (纸本)9780999241165

Exploring evidence from relevant articles to confirm the veracity of claims is a trend towards explainable claim verification. However, most strategies capture the top-k check-worthy articles or salient words as evidence, but this evidence is difficult to focus on the questionable parts of unverified claims. Besides, they utilize relevant articles indiscriminately, ignoring the source credibility of these articles, which may cause quiet a few unreliable articles to interfere with the assessment results. In this paper, we propose Evidence-aware Hierarchical Interactive Attention Networks (EHIAN) by considering the capture of evidence fragments and the fusion of source credibility to explore more credible evidence semantics discussing the questionable parts of claims for explainable claim verification. EHIAN first designs internal interaction layer (IIL) to strengthen deep interaction and matching between claims and relevant articles for obtaining key evidence fragments, and then proposes global inference layer (GIL) that fuses source features of articles and interacts globally with the average semantics of all articles and finally earns the more credible evidence semantics discussing the questionable parts of claims. Experiments on two datasets demonstrate that EHIAN not only achieves the state-of-the-art performance but also secures effective evidence to explain the results. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

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

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

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

Graph Explicit Attention Network Based on Predefined Strategy 12

Graph Explicit Attention Network Based on Predefined Strateg...

引用

12th International Conference on Identification, Information and Knowledge in the internet of Things, IIKI 2021

作者： Zhang, Xiangbo Rao, Yuan Sun, Ling Lab of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China Shannxi Joint Key Laboratory for Artifact Intelligence Sub-Lab of Xi'an Jiaotong University China Research Institute of Xi'an Jiaotong University Shenzhen China

Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attention mechanism in graph domain. Particularly, the attention coefficients and the multi-head mechanism are calculated or introduced in the process of model training, which obviously increases the storage complexity. In this paper, we present a graph explicit attention network (GEAT), a novel graph attention architecture that leverage predefined strategy to calculate attention coefficients, which combine global structural and node feature information. In this way, GEAT can effectively reduce the storage complexity, improve the training efficiency and alleviate the over-smoothing problem of attention scores. Experiments on benchmark datasets — Core, Citeseer and Pubmed — demonstrate that our model outperforms the state-of-the-art methods with a clear margin in challenging classifcation tasks, while being computationally efficient. © 2022 The Authors. Published by Elsevier B.V.

关键词： Attention mechanism Deep Learning Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Discovering differential features: Adversarial learning for information credibility evaluation

arXiv

引用

arXiv 2019年

作者： Wu, Lianwei Rao, Yuan Nazir, Ambreen Jin, Haolin Lab of Social Intelligence Complexity Data Processing School of Software Engineering Xi’an Jiaotong University Xi’an710049 China

A series of deep learning approaches extract a large number of credibility features to detect fake news on the Internet. However, these extracted features still suffer from many irrelevant and noisy features that restrict severely the performance of the approaches. In this paper, we propose a novel model based on Adversarial Networks and inspirited by the Shared-Private model (ANSP), which aims at reducing common, irrelevant features from the extracted features for information credibility evaluation. Specifically, ANSP involves two tasks: one is to prevent the binary classification of true and false information for capturing common features relying on adversarial networks guided by reinforcement learning. Another extracts credibility features (henceforth, private features) from multiple types of credibility information and compares with the common features through two strategies, i.e., orthogonality constraints and KL-divergence for making the private features more differential. Experiments first on two six-label LIAR and Weibo datasets demonstrate that ANSP achieves the state-of-the-art performance, boosting the accuracy by 2.1%, 3.1%, respectively and then on four-label Twitter16 validate the robustness of the model with 1.8% performance improvements. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

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：