Text classification is a pivotal task in natural language understanding,and its performance has seen remarkable advancements with the rise of Pre-trained Language Models(PLMs).Recently,the proliferation of PLMs has ma...Text classification is a pivotal task in natural language understanding,and its performance has seen remarkable advancements with the rise of Pre-trained Language Models(PLMs).Recently,the proliferation of PLMs has made it increasingly challenging to choose the most suitable model for a given dataset.Since fine-tuning the sheer number of models is impractical,Transferability Estimation(TE)has become a promising solution to efficient model selection.Unlike current TE methods that focus solely on fixed and hard class assignments to evaluate the quality of model-encoded features,our approach further takes into account the intersample and inter-model variations represented by soft class assignments.We achieve this by utilizing class embeddings to predict posterior class assignments,with the logarithm of the maximum posterior evidence serving as the transferability score.Moreover,we found that the informative sub-space of the dataset can lead to more accurate calculation of soft class assignments,where we achieve efficient annotation of informative samples by eliciting the powerful judging ability of large language model.The resulting posterior evidence over the informative sub-space,LogIPE,enables us to capture subtle differences between models,enhancing the accuracy of model selection and validated by extensive experiments conducted on a wide range of text classification datasets as well as candidate PLMs.展开更多
WASP(Wallops Arc Second Pointer)是由美国国家航空航天局(NASA)开发的一种临近空间天文台亚角秒级指向系统,旨在构建可适配多类科学载荷的临近空间天文观测平台.WASP系统由指向控制系统(PCS)和星跟踪器子系统(CARDS)组成,该系统结合...WASP(Wallops Arc Second Pointer)是由美国国家航空航天局(NASA)开发的一种临近空间天文台亚角秒级指向系统,旨在构建可适配多类科学载荷的临近空间天文观测平台.WASP系统由指向控制系统(PCS)和星跟踪器子系统(CARDS)组成,该系统结合精密机械和电子组件,辅以超压气球技术,能在临近空间执行长时飞行任务,同时保持亚角秒级的指向精度.WASP系统的灵活性和标准化设计使其能够适配多种科学载荷,满足不同的任务需求.在空间科学领域,WASP系统的应用不仅拓宽了高空科学气球的研究范围,也为临近空间天文台的建设提供了创新方案,推动了对临近空间的探索.WASP系统的成功试飞和应用,为其在行星科学、天体物理学和地球观测等领域的应用奠定了基础,也为中国临近空间科学的发展提供了可靠的参考.展开更多
目的探讨亚厘米非小细胞肺癌气腔播散(spread through air space,STAS)与临床特征及影像学特征的相关性,构建nomogram风险预测模型,为亚厘米非小细胞肺癌患者术前规划提供参考。方法回顾性分析2022年1月—2023年10月于南京大学医学院附...目的探讨亚厘米非小细胞肺癌气腔播散(spread through air space,STAS)与临床特征及影像学特征的相关性,构建nomogram风险预测模型,为亚厘米非小细胞肺癌患者术前规划提供参考。方法回顾性分析2022年1月—2023年10月于南京大学医学院附属鼓楼医院接受手术治疗且术后病理确诊为亚厘米非小细胞肺癌患者的临床资料。根据病理诊断肿瘤是否伴随STAS,将其分为STAS阳性组以及STAS阴性组。收集两组患者的临床和影像资料,进行单因素logistic回归分析,将差异具有统计学意义的变量纳入多因素分析,最终筛选出肿瘤发生STAS的独立危险因素,并构建nomogram模型。根据约登指数计算出灵敏度和特异度,并通过曲线下面积(area under the curve,AUC)、校准曲线和决策曲线分析(decision curve analysis,DCA)评估模型的效能。结果共纳入112例患者。STAS阳性组17例,其中男11例、女6例,平均年龄(59.0±10.3)岁;STAS阴性组95例,其中男30例、女65例,平均年龄(56.8±10.3)岁。单因素logistic回归分析显示,男性、抗GAGE7抗体阳性、平均CT值、毛刺征与STAS的发生相关(P<0.05)。多因素logistic回归分析表明,STAS与男性[OR=5.974,95%CI(1.495,23.872)]、抗GAGE7抗体阳性[OR=11.760,95%CI(1.619,85.408)]和平均CT值[OR=1.008,95%CI(1.004,1.013)]相关性仍然显著(P<0.05),而与毛刺征的关联不再显著(P=0.438)。基于上述3项独立预测因素构建亚厘米非小细胞肺癌STAS的nomogram模型。模型AUC值为0.890,灵敏度为76.5%,特异度为91.6%,校准曲线拟合良好,提示对于STAS有较好的预测效能;DCA图显示模型具有临床实用性。结论男性、抗GAGE7抗体阳性和平均CT值是亚厘米非小细胞肺癌STAS的独立预测因素,本研究构建的nomogram模型具有良好的预测价值,对患者的术前规划具有参考意义。展开更多
基金supported in part by the National Natural Science Foundation of China(Grant No.62477001).
文摘Text classification is a pivotal task in natural language understanding,and its performance has seen remarkable advancements with the rise of Pre-trained Language Models(PLMs).Recently,the proliferation of PLMs has made it increasingly challenging to choose the most suitable model for a given dataset.Since fine-tuning the sheer number of models is impractical,Transferability Estimation(TE)has become a promising solution to efficient model selection.Unlike current TE methods that focus solely on fixed and hard class assignments to evaluate the quality of model-encoded features,our approach further takes into account the intersample and inter-model variations represented by soft class assignments.We achieve this by utilizing class embeddings to predict posterior class assignments,with the logarithm of the maximum posterior evidence serving as the transferability score.Moreover,we found that the informative sub-space of the dataset can lead to more accurate calculation of soft class assignments,where we achieve efficient annotation of informative samples by eliciting the powerful judging ability of large language model.The resulting posterior evidence over the informative sub-space,LogIPE,enables us to capture subtle differences between models,enhancing the accuracy of model selection and validated by extensive experiments conducted on a wide range of text classification datasets as well as candidate PLMs.
文摘WASP(Wallops Arc Second Pointer)是由美国国家航空航天局(NASA)开发的一种临近空间天文台亚角秒级指向系统,旨在构建可适配多类科学载荷的临近空间天文观测平台.WASP系统由指向控制系统(PCS)和星跟踪器子系统(CARDS)组成,该系统结合精密机械和电子组件,辅以超压气球技术,能在临近空间执行长时飞行任务,同时保持亚角秒级的指向精度.WASP系统的灵活性和标准化设计使其能够适配多种科学载荷,满足不同的任务需求.在空间科学领域,WASP系统的应用不仅拓宽了高空科学气球的研究范围,也为临近空间天文台的建设提供了创新方案,推动了对临近空间的探索.WASP系统的成功试飞和应用,为其在行星科学、天体物理学和地球观测等领域的应用奠定了基础,也为中国临近空间科学的发展提供了可靠的参考.
文摘目的探讨亚厘米非小细胞肺癌气腔播散(spread through air space,STAS)与临床特征及影像学特征的相关性,构建nomogram风险预测模型,为亚厘米非小细胞肺癌患者术前规划提供参考。方法回顾性分析2022年1月—2023年10月于南京大学医学院附属鼓楼医院接受手术治疗且术后病理确诊为亚厘米非小细胞肺癌患者的临床资料。根据病理诊断肿瘤是否伴随STAS,将其分为STAS阳性组以及STAS阴性组。收集两组患者的临床和影像资料,进行单因素logistic回归分析,将差异具有统计学意义的变量纳入多因素分析,最终筛选出肿瘤发生STAS的独立危险因素,并构建nomogram模型。根据约登指数计算出灵敏度和特异度,并通过曲线下面积(area under the curve,AUC)、校准曲线和决策曲线分析(decision curve analysis,DCA)评估模型的效能。结果共纳入112例患者。STAS阳性组17例,其中男11例、女6例,平均年龄(59.0±10.3)岁;STAS阴性组95例,其中男30例、女65例,平均年龄(56.8±10.3)岁。单因素logistic回归分析显示,男性、抗GAGE7抗体阳性、平均CT值、毛刺征与STAS的发生相关(P<0.05)。多因素logistic回归分析表明,STAS与男性[OR=5.974,95%CI(1.495,23.872)]、抗GAGE7抗体阳性[OR=11.760,95%CI(1.619,85.408)]和平均CT值[OR=1.008,95%CI(1.004,1.013)]相关性仍然显著(P<0.05),而与毛刺征的关联不再显著(P=0.438)。基于上述3项独立预测因素构建亚厘米非小细胞肺癌STAS的nomogram模型。模型AUC值为0.890,灵敏度为76.5%,特异度为91.6%,校准曲线拟合良好,提示对于STAS有较好的预测效能;DCA图显示模型具有临床实用性。结论男性、抗GAGE7抗体阳性和平均CT值是亚厘米非小细胞肺癌STAS的独立预测因素,本研究构建的nomogram模型具有良好的预测价值,对患者的术前规划具有参考意义。
