检索结果-南通市图书馆

Improving Extraction of Chinese Open Relations Using Pre-trained Language Model and knowledge enhancement

Data Intelligence 2023年第4期5卷 962-989页

作者： Chaojie Wen Xudong Jia Tao Chen Faculty of Intelligent Manufacturing Wuyi UniversityJiangmenGuangdongChina

Open Relation Extraction(ORE)is a task of extracting semantic relations from a text *** ORE systems have significantly improved their efficiency in obtaining Chinese relations,when compared with conventional systems which heavily depend on feature engineering or syntactic ***,the ORE systems do not use robust neural networks such as pre-trained language models to take advantage of large-scale unstructured data *** respons to this issue,a new system entitled Chinese Open Relation Extraction with knowledge enhancement(CORE-KE)is presented in this *** CORE-KE system employs a pre-trained language model(with the support of a Bidirectional Long Short-Term Memory(BiLSTM)layer and a Masked Conditional Random Field(Masked CRF)layer)on unstructured data in order to improve Chinese open relation *** descriptions in Wikidata and additional knowledge(in terms of triple facts)extracted from Chinese ORE datasets are used to fine-tune the pre-trained language *** addition,syntactic features are further adopted in the training stage of the CORE-KE system for knowledge *** results of the CORE-KE system on two large-scale datasets of open Chinese entities and relations demonstrate that the CORE-KE system is superior to other ORE *** F1-scores of the CORE-KE system on the two datasets have given a relative improvement of 20.1%and 1.3%,when compared with benchmark ORE systems,*** source code is available at https:/***/cjwen15/CORE-KE.

关键词： Chinese open relation extraction Pre-trained language model knowledge enhancement

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Method of Multimodal Emotion Recognition in Video Learning Based on knowledge enhancement

引用

Computer Systems Science & Engineering 2023年第11期47卷 1709-1732页

作者： Hanmin Ye Yinghui Zhou Xiaomei Tao School of Information Science and Engineering Guilin University of TechnologyGuilin541004China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of TechnologyGuilin541004China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal UniversityGuilin541004China

With the popularity of online learning and due to the significant influence of emotion on the learning effect,more and more researches focus on emotion recognition in online *** of the current research uses the comments of the learning platform or the learner’s expression for emotion *** research data on other modalities are *** of the studies also ignore the impact of instructional videos on learners and the guidance of knowledge on *** of the need for other modal research data,we construct a synchronous multimodal data set for analyzing learners’emotional states in online learning *** data set recorded the eye movement data and photoplethysmography(PPG)signals of 68 subjects and the instructional video they *** the problem of ignoring the instructional videos on learners and ignoring the knowledge,a multimodal emotion recognition method in video learning based on knowledge enhancement is *** method uses the knowledge-based features extracted from instructional videos,such as brightness,hue,saturation,the videos’clickthrough rate,and emotion generation time,to guide the emotion recognition process of physiological *** method uses Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM)networks to extract deeper emotional representation and spatiotemporal information from shallow *** model uses multi-head attention(MHA)mechanism to obtain critical information in the extracted deep ***,Temporal Convolutional Network(TCN)is used to learn the information in the deep features and knowledge-based ***-based features are used to supplement and enhance the deep features of physiological ***,the fully connected layer is used for emotion recognition,and the recognition accuracy reaches 97.51%.Compared with two recent researches,the accuracy improved by 8.57%and 2.11%,*** the four public data sets,our proposed method also achieves bett

关键词： Emotion recognition video learning physiological signal knowledge enhancement deep learning CNN LSTM TCN

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

knowledge enhancement and Question-Answering of Metallurgical Industry Based on Generative AI Large Models

Knowledge Enhancement and Question-Answering of Metallurgica...

引用

第35届中国过程控制会议

作者： Ronghui Liu Hao Ren Wei Cui Chunhua Yang Weihua Gui Xiaojun Liang Peng Tang2Jie Han School of Future Technology South China University of Technology Industrial Intelligence Basic Studio Peng Cheng Laboratory

The metallurgical industry, characterized as a typical process industry, exhibits features such as frequent changes in raw material compositions, severe fluctuations in operational conditions, and complex physicochemical reaction *** attributes result in the knowledge within the field being extensive and intricate, making centralized management and effective application challenging. Addressing these challenges, this paper introduces a method that leverages the expertise of local knowledge bases and the powerful semantic understanding and text generation capabilities of Generative AI Large Models(GLM) to enhance metallurgical industry knowledge and facilitate Question-Answering(Q&A). The approach includes: initially cleaning and deduplicating raw data from industrial literature, production manuals, and briefings to establish a local knowledge base for the metallurgical industry. Subsequently, the contents of the knowledge base are embedded using Word2vec technology to create a local vector library of knowledge. FAISS(Facebook AI Similarity Search) technology is then utilized to search for knowledge vectors similar to specific industrial problems. Finally, selected question vectors and knowledge base vectors are integrated into input prompts for the GLM, which then produces accurate and coherent answers. Experimental results indicate that this method significantly improves the accuracy of Question-Answering in the metallurgical industry.

关键词： Generative AI knowledge enhancement Large Language Models Metallurgical Industry Question-Answering

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Study on Short Text Matching Method Based on KS-BERT Algorithm

引用

印刷与数字媒体技术研究 2024年第5期 164-173页

作者： YANG Hao-wen SUN Mei-feng College of Information Engineering(Artificial Intelligence) Yangzhou UniversityYangzhou 225000China Guangling College Yangzhou UniversityYangzhou 225000China

To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this *** method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input ***,the match was determined based on the fusion result of the two *** results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE *** Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text *** BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.

关键词： Deep learning Short text matching Graph attention network knowledge enhancement

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：