In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple e...In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.展开更多
OBJECTIVE: To explore the effects of Chaihu Guizhi Ganjiang Decoction combined with standard triple therapy on treating H.pylori-related gastritis. METHODS: Eighty-two patients with H. pylori-related gastritis treated...OBJECTIVE: To explore the effects of Chaihu Guizhi Ganjiang Decoction combined with standard triple therapy on treating H.pylori-related gastritis. METHODS: Eighty-two patients with H. pylori-related gastritis treated in our hospital from January 2016 to December 2017 were selected according to the random number table method and divided into experimental group and control group, with 41 patients in each group. The control group was treated with standard triple therapy, while the experimental group was additionally treated with modified Chaihu Guizhi Ganjiang Decoction. The venous blood of one elbow was taken before and after treatment. The concentrations of serum CagA and Hp-NAP were detected by enzyme-linked immunosorbent assay(ELISA). The symptoms were evaluated according to the change of symptom scores before and after the intervention. The H.pylori eradication rate was calculated. RESULTS: There was no significant difference in CagA and Hp-NAP concentrations between the 2 groups before intervention(P > 0.05). After intervention, CagA and Hp-NAP concentrations in experimental group were(19.21±6.27) ng/L and(24.37±6.10) ng/L respectively which were lower than(25.81±7.14) ng/L and(32.09±5.73) ng/L of control group. The differences were statistically significant(P < 0.05). The total effective rate of major symptoms in experimental group was 39 cases(95.12%), which was significantly higher than that of the control group(31 cases, 75.61%). There was statistically significant difference between the 2 groups(P < 0.05). The eradication rate of H.pylori was 38 cases(92.68%) in the experimental group, which was significantly higher than 31 cases(75.61%) of the control group. The difference between the 2 groups was statistically significant(P < 0.05). CONCLUSION: Chaihu Guizhi Ganjiang Decoction combined with standard triple therapy can effectively reduce CagA, Hp-NAP of serum level in patients with H.pylori-related gastritis, improve efficacy of symptoms and eradication rate of H.pylori, and is worthy of clinical promotion.展开更多
Zhao (2003a) first established a congruence for any odd prime p>3, S(1,1,1;p)≡-2Bp-3 (mod p), which holds when p=3 evidently. In this paper, we consider finite triple harmonic sum S(α,β,γ;p) (mod p) is consider...Zhao (2003a) first established a congruence for any odd prime p>3, S(1,1,1;p)≡-2Bp-3 (mod p), which holds when p=3 evidently. In this paper, we consider finite triple harmonic sum S(α,β,γ;p) (mod p) is considered for all positive integers α,β,γ. We refer to w=α+β+γ as the weight of the sum, and show that if w is even, S(α,β,γ;p)≡0 (mod p) for p≥w+3; if w is odd, S(α,β,γ;p)≡rBp≥w (mod p) for p≥w, here r is an explicit rational number independent of p. A congruence of Catalan number is obtained as a special case.展开更多
The isothermal sections of the Nb Ti Si ternary system at 1?473?K and 1?373?K were determined by means of diffusion triple technique and electron microprobe analysis. By analyzing the diffusion layers in the diffusion...The isothermal sections of the Nb Ti Si ternary system at 1?473?K and 1?373?K were determined by means of diffusion triple technique and electron microprobe analysis. By analyzing the diffusion layers in the diffusion couples, the titanium silicides and niobium silicides forming in this system were identified. The results show that no ternary compounds formed in the Nb Ti Si ternary system at the test temperatures. The phase transformations occurring on cooling from 1?473?K to 1?373?K were discussed.展开更多
为了探讨5-甲基胞嘧啶(5-methylcytosine,m5C)相关基因在三阴性乳腺癌(triple negative breast cancer,TNBC)患者治疗及预后中的潜在价值,构建了基于m5C相关基因的预后预测模型,用于评估TNBC患者的预后和生存状况。从基因表达总库(gene ...为了探讨5-甲基胞嘧啶(5-methylcytosine,m5C)相关基因在三阴性乳腺癌(triple negative breast cancer,TNBC)患者治疗及预后中的潜在价值,构建了基于m5C相关基因的预后预测模型,用于评估TNBC患者的预后和生存状况。从基因表达总库(gene expression omnibus,GEO)数据库和癌症基因组图谱(the cancer genome atlas,TCGA)数据库中下载TNBC基因表达谱和相应的临床数据。通过Pearson分析确定了99个m5C相关基因,进一步采用单因素Cox分析鉴定出5个与预后有关的m5C相关基因(SLC6A14、BCL11A、UGT8、LMO4、PSAT1)并构建了风险评分(risk score)预测模型,根据风险评分中位值将患者划分为高风险组和低风险组。使用Kaplan-Meier(K-M)生存分析、受试者工作特征(receiver operating characteristic,ROC)曲线、多变量Cox回归分析、构建列线图和校准曲线评估了模型的预测效能。训练集和验证集的K-M生存曲线、受试者工作特征曲线下面积(area under the curve,AUC)分析均验证了模型具有良好的预测能力。多变量Cox回归分析显示,风险评分可作为独立的预后生物标志物。使用ssGSEA、免疫评分分析和化疗药物对高低风险组患者的半最大抑制浓度(half maximal inhibitory concentration,IC50)值差异分析显示,免疫细胞和免疫检查点基因以及大多数化疗药物的IC50值在不同风险组之间的表达存在显著差异。研究结果构建了基于5个m5C相关基因的风险评分预后预测模型,这将有助于阐明TNBC中m5C相关基因的作用机制,进而提供更有价值的预后及诊断的生物标志物和潜在的治疗靶点,为TNBC患者临床个性化治疗提供理论指导。展开更多
现有分阶段解码的实体关系抽取模型仍存在着阶段间特征融合不充分的问题,会增大曝光偏差对抽取性能的影响。为此,提出一种双关系预测和特征融合的实体关系抽取模型(entity relation extraction model with dual relation prediction and...现有分阶段解码的实体关系抽取模型仍存在着阶段间特征融合不充分的问题,会增大曝光偏差对抽取性能的影响。为此,提出一种双关系预测和特征融合的实体关系抽取模型(entity relation extraction model with dual relation prediction and feature fusion,DRPFF),该模型使用预训练的基于Transformer的双向编码表示模型(bidirectional encoder representation from transformers,BERT)对文本进行编码,并设计两阶段的双关系预测结构来减少抽取过程中错误三元组的生成。在阶段间通过门控线性单元(gated linear unit,GLU)和条件层规范化(conditional layer normalization,CLN)组合的结构来更好地融合实体之间的特征。在NYT和WebNLG这2个公开数据集上的试验结果表明,该模型相较于基线方法取得了更好的效果。展开更多
目的探讨三阴型乳腺癌(triple-negative breast cancer,TNBC)中FOXC1、SOX10的表达与临床病理特征的关系及其临床意义。方法收集90例TNBC、60例非特殊类型浸润性乳腺癌(invasive breast carcinoma of no special type,IBC-NST)、40例癌...目的探讨三阴型乳腺癌(triple-negative breast cancer,TNBC)中FOXC1、SOX10的表达与临床病理特征的关系及其临床意义。方法收集90例TNBC、60例非特殊类型浸润性乳腺癌(invasive breast carcinoma of no special type,IBC-NST)、40例癌旁正常乳腺组织石蜡标本,采用免疫组化法检测FOXC1、SOX10的表达,分析其与临床病理特征的关系并复习相关文献。结果FOXC1和SOX10在TNBC(82.2%、70.0%)中阳性率均明显高于IBC-NST(11.7%、13.3%)及癌旁正常乳腺组织(7.5%、0),差异有统计学意义。FOXC1表达与TNBC肿瘤最大径、组织学分级、淋巴结转移、Ki-67增殖指数高、预后分期均相关(P<0.05),SOX10表达与TNBC肿瘤最大径、组织学分级、Ki-67增殖指数高、预后分期均相关(P<0.05),且TNBC中FOXC1与SOX10表达呈正相关(R=0.71,P<0.001)。Kaplan-Meier结果示FOXC1与肿瘤无进展生存期相关(P<0.05)。结论FOXC1和SOX10在TNBC中高表达,两者参与TNBC的发生、发展,在侵袭转移中可能起协同作用,对预后判断有一定价值。展开更多
基金Science and Technology Innovation 2030-Major Project of“New Generation Artificial Intelligence”granted by Ministry of Science and Technology,Grant Number 2020AAA0109300.
文摘In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.
文摘OBJECTIVE: To explore the effects of Chaihu Guizhi Ganjiang Decoction combined with standard triple therapy on treating H.pylori-related gastritis. METHODS: Eighty-two patients with H. pylori-related gastritis treated in our hospital from January 2016 to December 2017 were selected according to the random number table method and divided into experimental group and control group, with 41 patients in each group. The control group was treated with standard triple therapy, while the experimental group was additionally treated with modified Chaihu Guizhi Ganjiang Decoction. The venous blood of one elbow was taken before and after treatment. The concentrations of serum CagA and Hp-NAP were detected by enzyme-linked immunosorbent assay(ELISA). The symptoms were evaluated according to the change of symptom scores before and after the intervention. The H.pylori eradication rate was calculated. RESULTS: There was no significant difference in CagA and Hp-NAP concentrations between the 2 groups before intervention(P > 0.05). After intervention, CagA and Hp-NAP concentrations in experimental group were(19.21±6.27) ng/L and(24.37±6.10) ng/L respectively which were lower than(25.81±7.14) ng/L and(32.09±5.73) ng/L of control group. The differences were statistically significant(P < 0.05). The total effective rate of major symptoms in experimental group was 39 cases(95.12%), which was significantly higher than that of the control group(31 cases, 75.61%). There was statistically significant difference between the 2 groups(P < 0.05). The eradication rate of H.pylori was 38 cases(92.68%) in the experimental group, which was significantly higher than 31 cases(75.61%) of the control group. The difference between the 2 groups was statistically significant(P < 0.05). CONCLUSION: Chaihu Guizhi Ganjiang Decoction combined with standard triple therapy can effectively reduce CagA, Hp-NAP of serum level in patients with H.pylori-related gastritis, improve efficacy of symptoms and eradication rate of H.pylori, and is worthy of clinical promotion.
基金Project (No. 10371107) supported by the National Natural Science Foundation of China
文摘Zhao (2003a) first established a congruence for any odd prime p>3, S(1,1,1;p)≡-2Bp-3 (mod p), which holds when p=3 evidently. In this paper, we consider finite triple harmonic sum S(α,β,γ;p) (mod p) is considered for all positive integers α,β,γ. We refer to w=α+β+γ as the weight of the sum, and show that if w is even, S(α,β,γ;p)≡0 (mod p) for p≥w+3; if w is odd, S(α,β,γ;p)≡rBp≥w (mod p) for p≥w, here r is an explicit rational number independent of p. A congruence of Catalan number is obtained as a special case.
文摘The isothermal sections of the Nb Ti Si ternary system at 1?473?K and 1?373?K were determined by means of diffusion triple technique and electron microprobe analysis. By analyzing the diffusion layers in the diffusion couples, the titanium silicides and niobium silicides forming in this system were identified. The results show that no ternary compounds formed in the Nb Ti Si ternary system at the test temperatures. The phase transformations occurring on cooling from 1?473?K to 1?373?K were discussed.
文摘为了探讨5-甲基胞嘧啶(5-methylcytosine,m5C)相关基因在三阴性乳腺癌(triple negative breast cancer,TNBC)患者治疗及预后中的潜在价值,构建了基于m5C相关基因的预后预测模型,用于评估TNBC患者的预后和生存状况。从基因表达总库(gene expression omnibus,GEO)数据库和癌症基因组图谱(the cancer genome atlas,TCGA)数据库中下载TNBC基因表达谱和相应的临床数据。通过Pearson分析确定了99个m5C相关基因,进一步采用单因素Cox分析鉴定出5个与预后有关的m5C相关基因(SLC6A14、BCL11A、UGT8、LMO4、PSAT1)并构建了风险评分(risk score)预测模型,根据风险评分中位值将患者划分为高风险组和低风险组。使用Kaplan-Meier(K-M)生存分析、受试者工作特征(receiver operating characteristic,ROC)曲线、多变量Cox回归分析、构建列线图和校准曲线评估了模型的预测效能。训练集和验证集的K-M生存曲线、受试者工作特征曲线下面积(area under the curve,AUC)分析均验证了模型具有良好的预测能力。多变量Cox回归分析显示,风险评分可作为独立的预后生物标志物。使用ssGSEA、免疫评分分析和化疗药物对高低风险组患者的半最大抑制浓度(half maximal inhibitory concentration,IC50)值差异分析显示,免疫细胞和免疫检查点基因以及大多数化疗药物的IC50值在不同风险组之间的表达存在显著差异。研究结果构建了基于5个m5C相关基因的风险评分预后预测模型,这将有助于阐明TNBC中m5C相关基因的作用机制,进而提供更有价值的预后及诊断的生物标志物和潜在的治疗靶点,为TNBC患者临床个性化治疗提供理论指导。
文摘现有分阶段解码的实体关系抽取模型仍存在着阶段间特征融合不充分的问题,会增大曝光偏差对抽取性能的影响。为此,提出一种双关系预测和特征融合的实体关系抽取模型(entity relation extraction model with dual relation prediction and feature fusion,DRPFF),该模型使用预训练的基于Transformer的双向编码表示模型(bidirectional encoder representation from transformers,BERT)对文本进行编码,并设计两阶段的双关系预测结构来减少抽取过程中错误三元组的生成。在阶段间通过门控线性单元(gated linear unit,GLU)和条件层规范化(conditional layer normalization,CLN)组合的结构来更好地融合实体之间的特征。在NYT和WebNLG这2个公开数据集上的试验结果表明,该模型相较于基线方法取得了更好的效果。
文摘目的探讨三阴型乳腺癌(triple-negative breast cancer,TNBC)中FOXC1、SOX10的表达与临床病理特征的关系及其临床意义。方法收集90例TNBC、60例非特殊类型浸润性乳腺癌(invasive breast carcinoma of no special type,IBC-NST)、40例癌旁正常乳腺组织石蜡标本,采用免疫组化法检测FOXC1、SOX10的表达,分析其与临床病理特征的关系并复习相关文献。结果FOXC1和SOX10在TNBC(82.2%、70.0%)中阳性率均明显高于IBC-NST(11.7%、13.3%)及癌旁正常乳腺组织(7.5%、0),差异有统计学意义。FOXC1表达与TNBC肿瘤最大径、组织学分级、淋巴结转移、Ki-67增殖指数高、预后分期均相关(P<0.05),SOX10表达与TNBC肿瘤最大径、组织学分级、Ki-67增殖指数高、预后分期均相关(P<0.05),且TNBC中FOXC1与SOX10表达呈正相关(R=0.71,P<0.001)。Kaplan-Meier结果示FOXC1与肿瘤无进展生存期相关(P<0.05)。结论FOXC1和SOX10在TNBC中高表达,两者参与TNBC的发生、发展,在侵袭转移中可能起协同作用,对预后判断有一定价值。
