Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
In Central Europe, a large portion of post-mining sites were afforested with Scots pine, which is characterized by good adaptability and a tolerance for poor habitat at the beginning of forest ecosystem development. C...In Central Europe, a large portion of post-mining sites were afforested with Scots pine, which is characterized by good adaptability and a tolerance for poor habitat at the beginning of forest ecosystem development. Conversion of monoculture on mine sites into more biodi- verse mixed hardwood forests, especially on more fertile deposits, can be an emerging need in this part of Europe in next decades. The ability to classify the forests at these post-mining sites will facilitate proper species selection as well as the management and formation of the developed ecosystem＇s stability. This work describes the guidelines that can be followed to assess reclaimed mine soil （RMS） quality, using the mine soil quality index （MSQI） and a classification of developed forest sites as a basis of tree-stand species selection and conversion of pine monocul- tures. The research was conducted on four post-mining facilities （lignite, hard coal, sulphur, and sand pit mining areas） on different RMS sub- strates dominant in Central Europe. Soil quality assessment takes into account the following features of the soil： texture soil nutrients （Ca, Mg, K, Na, P）; acidity （pH KC1）; and Corg-to-Nt ratio in the initial organic horizon. An analysis was conducted of classification systems using the MSQI validation correlation （at p =0.05） with vegetation features af- fected by succession： aboveground biomass of forest floor and ecological indicators of vascular plants （calculated on the basis of EUenberg＇s （2009） system）. Eventually, in the analysed data set, the MSQI ranged from 0.270 for soils on quaternary sands to 0.720 for a mix of quaternary loamy sands with neogene clays. Potential forest habitat types and the role of the pine in the next generation of tree stands on different RMS parent rock substrate were proposed.展开更多
Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent ...Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent years.However,it is a challenging task for machines to conduct emotion classification in textual conversations because emotions rely heavily on textual context.To address the challenge,we propose a method to classify emotion in textual conversations,by integrating the advantages of deep learning and broad learning,namely DBL.It aims to provide a more effective solution to capture local contextual information(i.e.,utterance-level)in an utterance,as well as global contextual information(i.e.,speaker-level)in a conversation,based on Convolutional Neural Network(CNN),Bidirectional Long Short-Term Memory(Bi-LSTM),and broad learning.Extensive experiments have been conducted on three public textual conversation datasets,which show that the context in both utterance-level and speaker-level is consistently beneficial to the performance of emotion classification.In addition,the results show that our proposed method outperforms the baseline methods on most of the testing datasets in weighted-average F1.展开更多
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
基金financially supported by the Polish Ministry of Science and Higher Education Grant N 309 013 32/2076partly by statutory financial support of the Ministry of Science and Higher Education RP(DS-3420 in 2012 and 2013,Department of Forest Ecology University of Agriculture in Krakow
文摘In Central Europe, a large portion of post-mining sites were afforested with Scots pine, which is characterized by good adaptability and a tolerance for poor habitat at the beginning of forest ecosystem development. Conversion of monoculture on mine sites into more biodi- verse mixed hardwood forests, especially on more fertile deposits, can be an emerging need in this part of Europe in next decades. The ability to classify the forests at these post-mining sites will facilitate proper species selection as well as the management and formation of the developed ecosystem＇s stability. This work describes the guidelines that can be followed to assess reclaimed mine soil （RMS） quality, using the mine soil quality index （MSQI） and a classification of developed forest sites as a basis of tree-stand species selection and conversion of pine monocul- tures. The research was conducted on four post-mining facilities （lignite, hard coal, sulphur, and sand pit mining areas） on different RMS sub- strates dominant in Central Europe. Soil quality assessment takes into account the following features of the soil： texture soil nutrients （Ca, Mg, K, Na, P）; acidity （pH KC1）; and Corg-to-Nt ratio in the initial organic horizon. An analysis was conducted of classification systems using the MSQI validation correlation （at p =0.05） with vegetation features af- fected by succession： aboveground biomass of forest floor and ecological indicators of vascular plants （calculated on the basis of EUenberg＇s （2009） system）. Eventually, in the analysed data set, the MSQI ranged from 0.270 for soils on quaternary sands to 0.720 for a mix of quaternary loamy sands with neogene clays. Potential forest habitat types and the role of the pine in the next generation of tree stands on different RMS parent rock substrate were proposed.
基金supported by the National Natural Science Foundation of China(No.61876205)the National Key Research and Development Program of China(No.2020YFB1005804)the MOE Project at Center for Linguistics and Applied Linguistics,Guangdong University of Foreign Studies.
文摘Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent years.However,it is a challenging task for machines to conduct emotion classification in textual conversations because emotions rely heavily on textual context.To address the challenge,we propose a method to classify emotion in textual conversations,by integrating the advantages of deep learning and broad learning,namely DBL.It aims to provide a more effective solution to capture local contextual information(i.e.,utterance-level)in an utterance,as well as global contextual information(i.e.,speaker-level)in a conversation,based on Convolutional Neural Network(CNN),Bidirectional Long Short-Term Memory(Bi-LSTM),and broad learning.Extensive experiments have been conducted on three public textual conversation datasets,which show that the context in both utterance-level and speaker-level is consistently beneficial to the performance of emotion classification.In addition,the results show that our proposed method outperforms the baseline methods on most of the testing datasets in weighted-average F1.
