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
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
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.
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.
