With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions...With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying reasons.This comprehension is crucial for making informed strategic decisions in various business and societal contexts.However,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause extraction.To address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment mechanisms.The model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause pairs.Second,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among tasks.The proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 score.Experimental results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its effectiveness.This research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-cause pair extraction.However,the study’s limitation lies in the data sources,potentially restricting the generalizability of the findings.展开更多
Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the availa...Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model.展开更多
Objective:Using Chinese patents in force to investigate the frequency and patterns of Chinese herbal extract combinations claiming to treat heart disease.Methods:Patent documents were retrieved from the official websi...Objective:Using Chinese patents in force to investigate the frequency and patterns of Chinese herbal extract combinations claiming to treat heart disease.Methods:Patent documents were retrieved from the official website of the State Intellectual Property Office of the People’s Republic China.Cluster,frequency,and fuzzy cluster analyses were applied.Results:A high number of patents in force included high-frequency herbs such as Salvia miltiorrhiza,Panax ginseng,and Panax notoginseng,as well as high-frequency herbal families such as Araliaceae,Leguminosae,Labiatae,and Umbelliferae.Herb pairs such as P.ginsengþOphiopogon japonicus,S.miltiorrhizaþDalbergia odorifera,and P.ginsengþSchisandra chinensis are also commonly used,as well as herbal family pairs such as AraliaceaeþLiliaceae,LauraceaeþLeguminosae,and AraliaceaeþSchisandraceae.Traditional treatment principles for preventing and treating heart diseases was most-commonly based on simultaneously treating the liver and heart and treating the lung and spleen secondarily for choosing herbal combinations.Conclusion:Most of the high-frequency Chinese herbs in the patents investigated belong to the high-frequency herbal families,and herb pairs were commonly selected to coincide with the commonly-used herbal family pairs.Low-frequency Chinese herbs were also used,but generally belonged to the high-frequency herbal families,and were therefore similar to the highfrequency herbs in terms of traditional categories of taste and channel entered.The results reflect the use of traditional principles of formula composition,and suggest that these principles may indeed be an effective guide for further research and development of Chinese herbal extract combinations to prevent and treat heart diseases.展开更多
The investigation on UV-visible spectra of species formed by extracting some metal picrates with benzo-15-crown-5(B15C5) and dibenzo-18-crown-6(DB18C6) verified that there are some interactions of picrate anion with K...The investigation on UV-visible spectra of species formed by extracting some metal picrates with benzo-15-crown-5(B15C5) and dibenzo-18-crown-6(DB18C6) verified that there are some interactions of picrate anion with K+, Na+ and rare earth ions in loaded organic phase. By the study of the charge transfer band and absorption spectra of picrate anion, it can be determined whether an ion pair has been formed and either a 1 : 1 contact ion pair or a 1 : 2 crown-separated ion pair involved in organic phase can be distinguished for an ion-pair extraction.展开更多
Emotion-cause pair extraction(ECPE)aims to extract all the pairs of emotions and corresponding causes in a document.It generally contains three subtasks,emotions extraction,causes extraction,and causal relations detec...Emotion-cause pair extraction(ECPE)aims to extract all the pairs of emotions and corresponding causes in a document.It generally contains three subtasks,emotions extraction,causes extraction,and causal relations detection between emotions and causes.Existing works adopt pipelined approaches or multi-task learning to address the ECPE task.However,the pipelined approaches easily suffer from error propagation in real-world scenarios.Typical multi-task learning cannot optimize all tasks globally and may lead to suboptimal extraction results.To address these issues,we propose a novel framework,Pairwise Tagging Framework(PTF),tackling the complete emotion-cause pair extraction in one unified tagging task.Unlike prior works,PTF innovatively transforms all subtasks of ECPE,i.e.,emotions extraction,causes extraction,and causal relations detection between emotions and causes,into one unified clause-pair tagging task.Through this unified tagging task,we can optimize the ECPE task globally and extract more accurate emotion-cause pairs.To validate the feasibility and effectiveness of PTF,we design an end-to-end PTF-based neural network and conduct experiments on the ECPE benchmark dataset.The experimental results show that our method outperforms pipelined approaches significantly and typical multi-task learning approaches.展开更多
基于奇异值分解(Singular value decomposition,SVD)重构能够有效分离和抑制监测信号中的随机噪声分量,但其性能受限于轨迹矩阵的构造、有效分量评估选择等因素的影响。针对该问题,提出了一种基于最小互信息(Min mutual information,MMI...基于奇异值分解(Singular value decomposition,SVD)重构能够有效分离和抑制监测信号中的随机噪声分量,但其性能受限于轨迹矩阵的构造、有效分量评估选择等因素的影响。针对该问题,提出了一种基于最小互信息(Min mutual information,MMI)自适应累加奇异值子对(Sum singular value pairs,SSVP)优化框架并应用于机床轴承故障信号的特征提取。首先,采用反对角平均法计算奇异值(Singular value,SV)和奇异值向量,利用SV对子信号能量的表征能力得到奇异值子对(Singular value pairs,SVP);然后,基于MMI指标自适应获取最佳重构分量,避免了过降噪或欠降噪;同时,利用MMI和奇异值比(Singular value ratio,SVR)指标联合确定Hankel矩阵的最优分解维数。最后利用主轴故障轴承数据以及工业现场某加工中心进给系统轴承故障数据验证了MMI-SSVP方法的有效性。展开更多
随着人工智能技术的快速发展,深度学习在图形识别领域的应用日益广泛.作为一种高效的实时物体检测框架,YOLO(You Only Look Once)系列算法因其出色的性能和速度优势被广泛应用于多种视觉识别任务.在实际应用中,YOLOv5虽然非常高效,但仍...随着人工智能技术的快速发展,深度学习在图形识别领域的应用日益广泛.作为一种高效的实时物体检测框架,YOLO(You Only Look Once)系列算法因其出色的性能和速度优势被广泛应用于多种视觉识别任务.在实际应用中,YOLOv5虽然非常高效,但仍然存在计算负担较重、实时性差、过拟合等问题.如何优化其效率和精度,成为一个重要的研究方向.文中提出了一种基于YOLOv5优化的高效图形识别算法,旨在实现对图像中物体颜色与形状的提取、配对及统计分析.首先,采用YOLOv5模型识别图像中的多个物体,并提取每个物体的颜色和形状特征.然后,通过计算颜色与形状之间的距离,找出最小距离的配对.最后,根据配对结果,结合分类方法对颜色和形状的组合进行统计分析.实验结果表明,所提算法能在不同数据集上有效提高物体识别精度,并能准确地进行颜色与形状的组合统计,为智能物体识别系统的应用提供了新的思路.展开更多
文摘With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying reasons.This comprehension is crucial for making informed strategic decisions in various business and societal contexts.However,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause extraction.To address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment mechanisms.The model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause pairs.Second,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among tasks.The proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 score.Experimental results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its effectiveness.This research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-cause pair extraction.However,the study’s limitation lies in the data sources,potentially restricting the generalizability of the findings.
基金This work was supported by the National Natural Science Foundation of China(No.61672301)Jilin Provincial Science&Technology Development(20180101054JC)+1 种基金Science and Technology Innovation Guide Project of Inner Mongolia Autonomous Region of China(2017)Talent Development Fund of Jilin Province(2018).
文摘Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model.
文摘Objective:Using Chinese patents in force to investigate the frequency and patterns of Chinese herbal extract combinations claiming to treat heart disease.Methods:Patent documents were retrieved from the official website of the State Intellectual Property Office of the People’s Republic China.Cluster,frequency,and fuzzy cluster analyses were applied.Results:A high number of patents in force included high-frequency herbs such as Salvia miltiorrhiza,Panax ginseng,and Panax notoginseng,as well as high-frequency herbal families such as Araliaceae,Leguminosae,Labiatae,and Umbelliferae.Herb pairs such as P.ginsengþOphiopogon japonicus,S.miltiorrhizaþDalbergia odorifera,and P.ginsengþSchisandra chinensis are also commonly used,as well as herbal family pairs such as AraliaceaeþLiliaceae,LauraceaeþLeguminosae,and AraliaceaeþSchisandraceae.Traditional treatment principles for preventing and treating heart diseases was most-commonly based on simultaneously treating the liver and heart and treating the lung and spleen secondarily for choosing herbal combinations.Conclusion:Most of the high-frequency Chinese herbs in the patents investigated belong to the high-frequency herbal families,and herb pairs were commonly selected to coincide with the commonly-used herbal family pairs.Low-frequency Chinese herbs were also used,but generally belonged to the high-frequency herbal families,and were therefore similar to the highfrequency herbs in terms of traditional categories of taste and channel entered.The results reflect the use of traditional principles of formula composition,and suggest that these principles may indeed be an effective guide for further research and development of Chinese herbal extract combinations to prevent and treat heart diseases.
文摘The investigation on UV-visible spectra of species formed by extracting some metal picrates with benzo-15-crown-5(B15C5) and dibenzo-18-crown-6(DB18C6) verified that there are some interactions of picrate anion with K+, Na+ and rare earth ions in loaded organic phase. By the study of the charge transfer band and absorption spectra of picrate anion, it can be determined whether an ion pair has been formed and either a 1 : 1 contact ion pair or a 1 : 2 crown-separated ion pair involved in organic phase can be distinguished for an ion-pair extraction.
基金supported by the National Natural Science Foundation of China(NSFC)(Grant Nos.61976114 and 61936012)the National Key R&D Program of China(2018YFB1005102).
文摘Emotion-cause pair extraction(ECPE)aims to extract all the pairs of emotions and corresponding causes in a document.It generally contains three subtasks,emotions extraction,causes extraction,and causal relations detection between emotions and causes.Existing works adopt pipelined approaches or multi-task learning to address the ECPE task.However,the pipelined approaches easily suffer from error propagation in real-world scenarios.Typical multi-task learning cannot optimize all tasks globally and may lead to suboptimal extraction results.To address these issues,we propose a novel framework,Pairwise Tagging Framework(PTF),tackling the complete emotion-cause pair extraction in one unified tagging task.Unlike prior works,PTF innovatively transforms all subtasks of ECPE,i.e.,emotions extraction,causes extraction,and causal relations detection between emotions and causes,into one unified clause-pair tagging task.Through this unified tagging task,we can optimize the ECPE task globally and extract more accurate emotion-cause pairs.To validate the feasibility and effectiveness of PTF,we design an end-to-end PTF-based neural network and conduct experiments on the ECPE benchmark dataset.The experimental results show that our method outperforms pipelined approaches significantly and typical multi-task learning approaches.
文摘基于奇异值分解(Singular value decomposition,SVD)重构能够有效分离和抑制监测信号中的随机噪声分量,但其性能受限于轨迹矩阵的构造、有效分量评估选择等因素的影响。针对该问题,提出了一种基于最小互信息(Min mutual information,MMI)自适应累加奇异值子对(Sum singular value pairs,SSVP)优化框架并应用于机床轴承故障信号的特征提取。首先,采用反对角平均法计算奇异值(Singular value,SV)和奇异值向量,利用SV对子信号能量的表征能力得到奇异值子对(Singular value pairs,SVP);然后,基于MMI指标自适应获取最佳重构分量,避免了过降噪或欠降噪;同时,利用MMI和奇异值比(Singular value ratio,SVR)指标联合确定Hankel矩阵的最优分解维数。最后利用主轴故障轴承数据以及工业现场某加工中心进给系统轴承故障数据验证了MMI-SSVP方法的有效性。
文摘随着人工智能技术的快速发展,深度学习在图形识别领域的应用日益广泛.作为一种高效的实时物体检测框架,YOLO(You Only Look Once)系列算法因其出色的性能和速度优势被广泛应用于多种视觉识别任务.在实际应用中,YOLOv5虽然非常高效,但仍然存在计算负担较重、实时性差、过拟合等问题.如何优化其效率和精度,成为一个重要的研究方向.文中提出了一种基于YOLOv5优化的高效图形识别算法,旨在实现对图像中物体颜色与形状的提取、配对及统计分析.首先,采用YOLOv5模型识别图像中的多个物体,并提取每个物体的颜色和形状特征.然后,通过计算颜色与形状之间的距离,找出最小距离的配对.最后,根据配对结果,结合分类方法对颜色和形状的组合进行统计分析.实验结果表明,所提算法能在不同数据集上有效提高物体识别精度,并能准确地进行颜色与形状的组合统计,为智能物体识别系统的应用提供了新的思路.
