Medical visual question answering(MedVQA)aims to enhance diagnostic confidence and deepen patientsunderstanding of their health conditions.While the Transformer architecture is widely used in multimodal fields,its app...Medical visual question answering(MedVQA)aims to enhance diagnostic confidence and deepen patientsunderstanding of their health conditions.While the Transformer architecture is widely used in multimodal fields,its application in MedVQA requires further enhancement.A critical limitation of contemporary MedVQA systems lies in the inability to integrate lifelong knowledge with specific patient data to generate human-like responses.Existing Transformer-based MedVQA models require enhancing their capabitities for interpreting answers through the applications of medical image knowledge.The introduction of the medical knowledge graph visual language transformer(MKGViLT),designed for joint medical knowledge graphs(KGs),addresses this challenge.MKGViLT incorporates an enhanced Transformer structure to effectively extract features and combine modalities for MedVQA tasks.The MKGViLT model delivers answers based on richer background knowledge,thereby enhancing performance.The efficacy of MKGViLT is evaluated using the SLAKE and P-VQA datasets.Experimental results show that MKGViLT surpasses the most advanced methods on the SLAKE dataset.展开更多
Tracking and analyzing data from research projects is critical for understanding research trends and supporting the development of science and technology strategies.However,the data from these projects is often comple...Tracking and analyzing data from research projects is critical for understanding research trends and supporting the development of science and technology strategies.However,the data from these projects is often complex and inadequate,making it challenging for researchers to conduct in-depth data mining to improve policies or management.To address this problem,this paper adopts a top-down approach to construct a knowledge graph(KG)for research projects.Firstly,we construct an integrated ontology by referring to the metamodel of various architectures,which is called the meta-model integration conceptual reference model.Subsequently,we use the dependency parsing method to extract knowledge from unstructured textual data and use the entity alignment method based on weakly supervised learning to classify the extracted entities,completing the construction of the KG for the research projects.In addition,a knowledge inference model based on representation learning is employed to achieve knowledge completion and improve the KG.Finally,experiments are conducted on the KG for research projects and the results demonstrate the effectiveness of the proposed method in enriching incomplete data within the KG.展开更多
Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured framework.This framework facilitates a transformation in information ...Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured framework.This framework facilitates a transformation in information retrieval,transitioning it from mere string matching to far more sophisticated entity matching.In this transformative process,the advancement of artificial intelligence and intelligent information services is invigorated.Meanwhile,the role ofmachine learningmethod in the construction of KG is important,and these techniques have already achieved initial success.This article embarks on a comprehensive journey through the last strides in the field of KG via machine learning.With a profound amalgamation of cutting-edge research in machine learning,this article undertakes a systematical exploration of KG construction methods in three distinct phases:entity learning,ontology learning,and knowledge reasoning.Especially,a meticulous dissection of machine learningdriven algorithms is conducted,spotlighting their contributions to critical facets such as entity extraction,relation extraction,entity linking,and link prediction.Moreover,this article also provides an analysis of the unresolved challenges and emerging trajectories that beckon within the expansive application of machine learning-fueled,large-scale KG construction.展开更多
Accurately recommending candidate news to users is a basic challenge of personalized news recommendation systems.Traditional methods are usually difficult to learn and acquire complex semantic information in news text...Accurately recommending candidate news to users is a basic challenge of personalized news recommendation systems.Traditional methods are usually difficult to learn and acquire complex semantic information in news texts,resulting in unsatisfactory recommendation results.Besides,these traditional methods are more friendly to active users with rich historical behaviors.However,they can not effectively solve the long tail problem of inactive users.To address these issues,this research presents a novel general framework that combines Large Language Models(LLM)and Knowledge Graphs(KG)into traditional methods.To learn the contextual information of news text,we use LLMs’powerful text understanding ability to generate news representations with rich semantic information,and then,the generated news representations are used to enhance the news encoding in traditional methods.In addition,multi-hops relationship of news entities is mined and the structural information of news is encoded using KG,thus alleviating the challenge of long-tail distribution.Experimental results demonstrate that compared with various traditional models,on evaluation indicators such as AUC,MRR,nDCG@5 and nDCG@10,the framework significantly improves the recommendation performance.The successful integration of LLM and KG in our framework has established a feasible way for achieving more accurate personalized news recommendation.Our code is available at https://github.com/Xuan-ZW/LKPNR.展开更多
大语言模型(large language model,LLM)随着不断发展,在开放领域取得了出色的表现.然而,由于缺乏专业知识,LLM在垂直领域问答任务上效果较差.这一问题引发了研究者的广泛关注.现有研究通过“检索-问答”的方式,将领域知识注入大语言模型...大语言模型(large language model,LLM)随着不断发展,在开放领域取得了出色的表现.然而,由于缺乏专业知识,LLM在垂直领域问答任务上效果较差.这一问题引发了研究者的广泛关注.现有研究通过“检索-问答”的方式,将领域知识注入大语言模型,以增强其性能.然而该方式通常会检索到额外的噪声数据而导致LLM的性能损失.为了解决该问题,提出基于知识相关性的知识图谱问答方法.具体而言,将噪声数据与回答问题所需要的知识进行区分,在“检索-相关性评估-问答”的框架下,引导大语言模型选择合理的知识做出正确的回答.此外,提出一个机械领域知识图谱问答的数据集Mecha-QA,包含传统机械制造以及增材制造两个子领域,以推进该领域大语言模型与知识图谱问答相关的研究.为了验证所提方法的有效性,在Mecha-QA和航空航天领域数据集Aero-QA上进行实验.结果表明,该方法可以显著提升大语言模型在垂直领域知识图谱问答的性能.展开更多
针对知识推理模型在捕获实体之间的复杂语义特征方面难以捕捉多层次语义信息,同时未考虑单一路径的可解释性对正确答案的影响权重不同等问题,提出一种融合路径与子图特征的知识图谱(KG)多跳推理模型PSHAM(Hierarchical Attention Model ...针对知识推理模型在捕获实体之间的复杂语义特征方面难以捕捉多层次语义信息,同时未考虑单一路径的可解释性对正确答案的影响权重不同等问题,提出一种融合路径与子图特征的知识图谱(KG)多跳推理模型PSHAM(Hierarchical Attention Model fusing Path-Subgraph features)。PS-HAM将实体邻域信息与连接路径信息进行融合,并针对不同路径探索多粒度的特征。首先,使用路径级特征提取模块提取每个实体对之间的连接路径,并采用分层注意力机制捕获不同粒度的信息,且将这些信息作为路径级的表示;其次,使用子图特征提取模块通过关系图卷积网络(RGCN)聚合实体的邻域信息;最后,使用路径-子图特征融合模块对路径级与子图级特征向量进行融合,以实现融合推理。在两个公开数据集上进行实验的结果表明,PS-HAM在指标平均倒数秩(MRR)和Hit@k(k=1,3,10)上的性能均存在有效提升。对于指标MRR,与MemoryPath模型相比,PS-HAM在FB15k-237和WN18RR数据集上分别提升了1.5和1.2个百分点。同时,对子图跳数进行的参数验证的结果表明,PS-HAM在两个数据集上都在子图跳数在3时推理效果达到最佳。展开更多
传统的基于表示学习的知识推理方法只能用于封闭世界的知识推理,有效进行开放世界的知识推理是目前的热点问题。因此,提出一种基于路径和增强三元组文本的开放世界知识推理模型PEOR(Path and Enhanced triplet text for Open world know...传统的基于表示学习的知识推理方法只能用于封闭世界的知识推理,有效进行开放世界的知识推理是目前的热点问题。因此,提出一种基于路径和增强三元组文本的开放世界知识推理模型PEOR(Path and Enhanced triplet text for Open world knowledge Reasoning)。首先,使用由实体对间结构生成的多条路径和单个实体周围结构生成的增强三元组,其中路径文本通过拼接路径中的三元组文本得到,而增强三元组文本通过拼接头实体邻域文本、关系文本和尾实体邻域文本得到;其次,使用BERT(Bidirectional Encoder Representations from Transformers)分别编码路径文本和增强三元组文本;最后,使用路径向量和三元组向量计算语义匹配注意力,再使用语义匹配注意力聚合多条路径的语义信息。在3个开放世界知识图谱数据集WN18RR、FB15k-237和NELL-995上的对比实验结果表明,与次优模型BERTRL(BERT-based Relational Learning)相比,所提模型的命中率(Hits@10)指标分别提升了2.6、2.3和8.5个百分点,验证了所提模型的有效性。展开更多
基金Supported by the National Natural Science Foundation of China(No.62001313)the Liaoning Professional Talent Protect(No.XLYC2203046)the Shenyang Municipal Medical Engineering Cross Research Foundation of China(No.22-321-32-09).
文摘Medical visual question answering(MedVQA)aims to enhance diagnostic confidence and deepen patientsunderstanding of their health conditions.While the Transformer architecture is widely used in multimodal fields,its application in MedVQA requires further enhancement.A critical limitation of contemporary MedVQA systems lies in the inability to integrate lifelong knowledge with specific patient data to generate human-like responses.Existing Transformer-based MedVQA models require enhancing their capabitities for interpreting answers through the applications of medical image knowledge.The introduction of the medical knowledge graph visual language transformer(MKGViLT),designed for joint medical knowledge graphs(KGs),addresses this challenge.MKGViLT incorporates an enhanced Transformer structure to effectively extract features and combine modalities for MedVQA tasks.The MKGViLT model delivers answers based on richer background knowledge,thereby enhancing performance.The efficacy of MKGViLT is evaluated using the SLAKE and P-VQA datasets.Experimental results show that MKGViLT surpasses the most advanced methods on the SLAKE dataset.
基金supported by the National Natural Science Foundation of China(72101263).
文摘Tracking and analyzing data from research projects is critical for understanding research trends and supporting the development of science and technology strategies.However,the data from these projects is often complex and inadequate,making it challenging for researchers to conduct in-depth data mining to improve policies or management.To address this problem,this paper adopts a top-down approach to construct a knowledge graph(KG)for research projects.Firstly,we construct an integrated ontology by referring to the metamodel of various architectures,which is called the meta-model integration conceptual reference model.Subsequently,we use the dependency parsing method to extract knowledge from unstructured textual data and use the entity alignment method based on weakly supervised learning to classify the extracted entities,completing the construction of the KG for the research projects.In addition,a knowledge inference model based on representation learning is employed to achieve knowledge completion and improve the KG.Finally,experiments are conducted on the KG for research projects and the results demonstrate the effectiveness of the proposed method in enriching incomplete data within the KG.
基金supported in part by the Beijing Natural Science Foundation under Grants L211020 and M21032in part by the National Natural Science Foundation of China under Grants U1836106 and 62271045in part by the Scientific and Technological Innovation Foundation of Foshan under Grants BK21BF001 and BK20BF010。
文摘Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured framework.This framework facilitates a transformation in information retrieval,transitioning it from mere string matching to far more sophisticated entity matching.In this transformative process,the advancement of artificial intelligence and intelligent information services is invigorated.Meanwhile,the role ofmachine learningmethod in the construction of KG is important,and these techniques have already achieved initial success.This article embarks on a comprehensive journey through the last strides in the field of KG via machine learning.With a profound amalgamation of cutting-edge research in machine learning,this article undertakes a systematical exploration of KG construction methods in three distinct phases:entity learning,ontology learning,and knowledge reasoning.Especially,a meticulous dissection of machine learningdriven algorithms is conducted,spotlighting their contributions to critical facets such as entity extraction,relation extraction,entity linking,and link prediction.Moreover,this article also provides an analysis of the unresolved challenges and emerging trajectories that beckon within the expansive application of machine learning-fueled,large-scale KG construction.
基金supported by National Key R&D Program of China(2022QY2000-02).
文摘Accurately recommending candidate news to users is a basic challenge of personalized news recommendation systems.Traditional methods are usually difficult to learn and acquire complex semantic information in news texts,resulting in unsatisfactory recommendation results.Besides,these traditional methods are more friendly to active users with rich historical behaviors.However,they can not effectively solve the long tail problem of inactive users.To address these issues,this research presents a novel general framework that combines Large Language Models(LLM)and Knowledge Graphs(KG)into traditional methods.To learn the contextual information of news text,we use LLMs’powerful text understanding ability to generate news representations with rich semantic information,and then,the generated news representations are used to enhance the news encoding in traditional methods.In addition,multi-hops relationship of news entities is mined and the structural information of news is encoded using KG,thus alleviating the challenge of long-tail distribution.Experimental results demonstrate that compared with various traditional models,on evaluation indicators such as AUC,MRR,nDCG@5 and nDCG@10,the framework significantly improves the recommendation performance.The successful integration of LLM and KG in our framework has established a feasible way for achieving more accurate personalized news recommendation.Our code is available at https://github.com/Xuan-ZW/LKPNR.
文摘大语言模型(large language model,LLM)随着不断发展,在开放领域取得了出色的表现.然而,由于缺乏专业知识,LLM在垂直领域问答任务上效果较差.这一问题引发了研究者的广泛关注.现有研究通过“检索-问答”的方式,将领域知识注入大语言模型,以增强其性能.然而该方式通常会检索到额外的噪声数据而导致LLM的性能损失.为了解决该问题,提出基于知识相关性的知识图谱问答方法.具体而言,将噪声数据与回答问题所需要的知识进行区分,在“检索-相关性评估-问答”的框架下,引导大语言模型选择合理的知识做出正确的回答.此外,提出一个机械领域知识图谱问答的数据集Mecha-QA,包含传统机械制造以及增材制造两个子领域,以推进该领域大语言模型与知识图谱问答相关的研究.为了验证所提方法的有效性,在Mecha-QA和航空航天领域数据集Aero-QA上进行实验.结果表明,该方法可以显著提升大语言模型在垂直领域知识图谱问答的性能.
文摘传统的基于表示学习的知识推理方法只能用于封闭世界的知识推理,有效进行开放世界的知识推理是目前的热点问题。因此,提出一种基于路径和增强三元组文本的开放世界知识推理模型PEOR(Path and Enhanced triplet text for Open world knowledge Reasoning)。首先,使用由实体对间结构生成的多条路径和单个实体周围结构生成的增强三元组,其中路径文本通过拼接路径中的三元组文本得到,而增强三元组文本通过拼接头实体邻域文本、关系文本和尾实体邻域文本得到;其次,使用BERT(Bidirectional Encoder Representations from Transformers)分别编码路径文本和增强三元组文本;最后,使用路径向量和三元组向量计算语义匹配注意力,再使用语义匹配注意力聚合多条路径的语义信息。在3个开放世界知识图谱数据集WN18RR、FB15k-237和NELL-995上的对比实验结果表明,与次优模型BERTRL(BERT-based Relational Learning)相比,所提模型的命中率(Hits@10)指标分别提升了2.6、2.3和8.5个百分点,验证了所提模型的有效性。
