Text Summarization models facilitate biomedical clinicians and researchers in acquiring informative data from enormous domain-specific literature within less time and effort.Evaluating and selecting the most informati...Text Summarization models facilitate biomedical clinicians and researchers in acquiring informative data from enormous domain-specific literature within less time and effort.Evaluating and selecting the most informative sentences from biomedical articles is always challenging.This study aims to develop a dual-mode biomedical text summarization model to achieve enhanced coverage and information.The research also includes checking the fitment of appropriate graph ranking techniques for improved performance of the summarization model.The input biomedical text is mapped as a graph where meaningful sentences are evaluated as the central node and the critical associations between them.The proposed framework utilizes the top k similarity technique in a combination of UMLS and a sampled probability-based clustering method which aids in unearthing relevant meanings of the biomedical domain-specific word vectors and finding the best possible associations between crucial sentences.The quality of the framework is assessed via different parameters like information retention,coverage,readability,cohesion,and ROUGE scores in clustering and non-clustering modes.The significant benefits of the suggested technique are capturing crucial biomedical information with increased coverage and reasonable memory consumption.The configurable settings of combined parameters reduce execution time,enhance memory utilization,and extract relevant information outperforming other biomedical baseline models.An improvement of 17%is achieved when the proposed model is checked against similar biomedical text summarizers.展开更多
The rank of a graph G is defined to be the rank of its adjacency matrix A（G）. In this paper we characterize all connected triangle-free graphs with rank 6.
The rank of a graph is defined to be the rank of its adjacency matrix. In this paper, the Matlab was used to explore the graphs with rank no more than 5;the performance of the proposed method was compared with former ...The rank of a graph is defined to be the rank of its adjacency matrix. In this paper, the Matlab was used to explore the graphs with rank no more than 5;the performance of the proposed method was compared with former methods, which is simpler and clearer;and the results show that all graphs with rank no more than 5 are characterized.展开更多
A graph is called an integral graph if it has an integral spectrum i.e.,all eigenvalues are integers.A graph is called circulant graph if it is Cayley graph on the circulant group,i.e.,its adjacency matrix is circulan...A graph is called an integral graph if it has an integral spectrum i.e.,all eigenvalues are integers.A graph is called circulant graph if it is Cayley graph on the circulant group,i.e.,its adjacency matrix is circulant.The rank of a graph is defined to be the rank of its adjacency matrix.This importance of the rank,due to applications in physics,chemistry and combinatorics.In this paper,using Ramanujan sums,we study the rank of integral circulant graphs and gave some simple computational formulas for the rank and provide an example which shows the formula is sharp.展开更多
Let G be a graph and A(G) the adjacency matrix of G. The spectrum of G is the eigenvalues together with their multiplicities of A(G). Chang et al. (2011) characterized the structures of all graphs with rank 4. Monsalv...Let G be a graph and A(G) the adjacency matrix of G. The spectrum of G is the eigenvalues together with their multiplicities of A(G). Chang et al. (2011) characterized the structures of all graphs with rank 4. Monsalve and Rada (2021) gave the bound of spectral radius of all graphs with rank 4. Based on these results as above, we further investigate the spectral properties of graphs with rank 4. And we give the expressions of the spectral radius and energy of all graphs with rank 4. In particular, we show that some graphs with rank 4 are determined by their spectra.展开更多
In this paper we study the relationship between minimum rank of graph G and the minimum rank of graph for some families of special graph G, where is the jth power of graph G.
为满足食品安全监管问答任务对模型准确性、合规性和可解释性的高要求,解决现有大语言模型(large language model,LLM)在该领域应用面临的知识召回不精准、法规解析能力不足及计算成本高等问题,本研究基于检索增强生成框架提出了一个智...为满足食品安全监管问答任务对模型准确性、合规性和可解释性的高要求,解决现有大语言模型(large language model,LLM)在该领域应用面临的知识召回不精准、法规解析能力不足及计算成本高等问题,本研究基于检索增强生成框架提出了一个智能问答系统,其核心是食品安全监管大语言模型(food safety regulation large language model,FSR-LLM)。通过优化数据库存储结构、检索策略及生成器,提升食品安全监管问答的质量和效率。首先构建了食品安全知识图谱(knowledge graph,KG)数据库,以结构化方式存储法规条款、食品安全标准等数据,增强模型对食品领域知识的组织与调用能力。此外,在检索阶段,设计一种大模型引导检索策略,利用LLM智能解析查询语句,在食品安全监管KG中准确地提取高度相关的信息,从而减少无关或误导性内容的召回。对于生成器(Generator)模块,基于Qwen-7B-Chat模型采用低秩适应微调,使模型更贴合食品安全监管问答的需求,同时显著降低计算成本,使其能够在单张RTX 4090 GPU上完成训练。在所提食品安全问答数据集上的实验结果表明,FSR-LLM在BLEU-4、Rouge-L和准确率指标上均优于基线模型,展现出更高的精准度和语义连贯性,为食品安全监管智能化提供了一种低成本、高效能、可扩展的解决方案。展开更多
文摘Text Summarization models facilitate biomedical clinicians and researchers in acquiring informative data from enormous domain-specific literature within less time and effort.Evaluating and selecting the most informative sentences from biomedical articles is always challenging.This study aims to develop a dual-mode biomedical text summarization model to achieve enhanced coverage and information.The research also includes checking the fitment of appropriate graph ranking techniques for improved performance of the summarization model.The input biomedical text is mapped as a graph where meaningful sentences are evaluated as the central node and the critical associations between them.The proposed framework utilizes the top k similarity technique in a combination of UMLS and a sampled probability-based clustering method which aids in unearthing relevant meanings of the biomedical domain-specific word vectors and finding the best possible associations between crucial sentences.The quality of the framework is assessed via different parameters like information retention,coverage,readability,cohesion,and ROUGE scores in clustering and non-clustering modes.The significant benefits of the suggested technique are capturing crucial biomedical information with increased coverage and reasonable memory consumption.The configurable settings of combined parameters reduce execution time,enhance memory utilization,and extract relevant information outperforming other biomedical baseline models.An improvement of 17%is achieved when the proposed model is checked against similar biomedical text summarizers.
基金National Natural Science Foundation of China(Grant Nos.1107100211371028)+3 种基金Program for NewCentury Excellent Talents in University(Grant No.NCET-10-0001)Key Project of Chinese Ministry of Education(Grant No.210091)Scientific Research Fund for Fostering Distinguished Young Scholars of Anhui University(Grant No.KJJQ1001)Academic Innovation Team of Anhui University Project(Grant No.KJTD001B)
文摘The rank of a graph G is defined to be the rank of its adjacency matrix A（G）. In this paper we characterize all connected triangle-free graphs with rank 6.
文摘The rank of a graph is defined to be the rank of its adjacency matrix. In this paper, the Matlab was used to explore the graphs with rank no more than 5;the performance of the proposed method was compared with former methods, which is simpler and clearer;and the results show that all graphs with rank no more than 5 are characterized.
基金Foundation item： Supported by Hunan Provincial Natural Science Foundation（13JJ3118）
文摘A graph is called an integral graph if it has an integral spectrum i.e.,all eigenvalues are integers.A graph is called circulant graph if it is Cayley graph on the circulant group,i.e.,its adjacency matrix is circulant.The rank of a graph is defined to be the rank of its adjacency matrix.This importance of the rank,due to applications in physics,chemistry and combinatorics.In this paper,using Ramanujan sums,we study the rank of integral circulant graphs and gave some simple computational formulas for the rank and provide an example which shows the formula is sharp.
文摘Let G be a graph and A(G) the adjacency matrix of G. The spectrum of G is the eigenvalues together with their multiplicities of A(G). Chang et al. (2011) characterized the structures of all graphs with rank 4. Monsalve and Rada (2021) gave the bound of spectral radius of all graphs with rank 4. Based on these results as above, we further investigate the spectral properties of graphs with rank 4. And we give the expressions of the spectral radius and energy of all graphs with rank 4. In particular, we show that some graphs with rank 4 are determined by their spectra.
文摘In this paper we study the relationship between minimum rank of graph G and the minimum rank of graph for some families of special graph G, where is the jth power of graph G.
文摘为满足食品安全监管问答任务对模型准确性、合规性和可解释性的高要求,解决现有大语言模型(large language model,LLM)在该领域应用面临的知识召回不精准、法规解析能力不足及计算成本高等问题,本研究基于检索增强生成框架提出了一个智能问答系统,其核心是食品安全监管大语言模型(food safety regulation large language model,FSR-LLM)。通过优化数据库存储结构、检索策略及生成器,提升食品安全监管问答的质量和效率。首先构建了食品安全知识图谱(knowledge graph,KG)数据库,以结构化方式存储法规条款、食品安全标准等数据,增强模型对食品领域知识的组织与调用能力。此外,在检索阶段,设计一种大模型引导检索策略,利用LLM智能解析查询语句,在食品安全监管KG中准确地提取高度相关的信息,从而减少无关或误导性内容的召回。对于生成器(Generator)模块,基于Qwen-7B-Chat模型采用低秩适应微调,使模型更贴合食品安全监管问答的需求,同时显著降低计算成本,使其能够在单张RTX 4090 GPU上完成训练。在所提食品安全问答数据集上的实验结果表明,FSR-LLM在BLEU-4、Rouge-L和准确率指标上均优于基线模型,展现出更高的精准度和语义连贯性,为食品安全监管智能化提供了一种低成本、高效能、可扩展的解决方案。
