At present,the entity and relation joint extraction task has attracted more and more scholars'attention in the field of natural language processing(NLP).However,most of their methods rely on NLP tools to construct...At present,the entity and relation joint extraction task has attracted more and more scholars'attention in the field of natural language processing(NLP).However,most of their methods rely on NLP tools to construct dependency trees to obtain sentence structure information.The adjacency matrix constructed by the dependency tree can convey syntactic information.Dependency trees obtained through NLP tools are too dependent on the tools and may not be very accurate in contextual semantic description.At the same time,a large amount of irrelevant information will cause redundancy.This paper presents a novel end-to-end entity and relation joint extraction based on the multihead attention graph convolutional network model(MAGCN),which does not rely on external tools.MAGCN generates an adjacency matrix through a multi-head attention mechanism to form an attention graph convolutional network model,uses head selection to identify multiple relations,and effectively improve the prediction result of overlapping relations.The authors extensively experiment and prove the method's effectiveness on three public datasets:NYT,WebNLG,and CoNLL04.The results show that the authors’method outperforms the state-of-the-art research results for the task of entities and relation extraction.展开更多
Electrode materials with good redox kinetics,excellent mass transfer characteristics and ultra-high stability play a crucial role in reducing the life-cycle cost and prolonging the maintenance-free time of the vanadiu...Electrode materials with good redox kinetics,excellent mass transfer characteristics and ultra-high stability play a crucial role in reducing the life-cycle cost and prolonging the maintenance-free time of the vanadium flow batteries(VFB).Herein,a nitrogen-doped porous graphite felt electrode(N-PGF)is proposed by growing ZIF-67 nanoparticles on carbon fibers and then calcinating and acid etching.The multi-scale structure of“carbon fiber gap(electrolyte flow),micro/nano pore(active species diffusion)and Nitrogen active center(reaction site)”in N-PGF electrode effectively increases the catalytic sites and promotes mass transfer characteristics.Reasonable electrode design makes the battery show excellent rate performance and ultra-high cycling stability.The peak power density of the battery reaches 1006 mW cm^(-2).During 1000 cycles at 150 mA cm^(-2),the average discharge capacity and average discharge energy of N-PGF increase substantially by 11.6%and 23.4%compared with the benchmark thermal activated graphite felt,respectively.More excitingly,after ultra-long term(5000 cycles)operation at an ultra-high current density(300 mA cm^(-2)),N-PGF exhibits an unprecedented energy efficiency retention(99.79%)and electrochemical performance stability.展开更多
Current Chinese event detection methods commonly use word embedding to capture semantic representation,but these methods find it difficult to capture the dependence relationship between the trigger words and other wor...Current Chinese event detection methods commonly use word embedding to capture semantic representation,but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence.Based on the simple evaluation,it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation.This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words.This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser.The authors evaluate different models on kbp 2017 corpus.The experimental results show that the proposed method can significantly improve performance in Chinese event detection.展开更多
Laser-induced breakdown spectroscopy has become a general-purpose technique, and internal standard calibration is a common method for quantitative analysis. Calibration models should be reconstructed for different sys...Laser-induced breakdown spectroscopy has become a general-purpose technique, and internal standard calibration is a common method for quantitative analysis. Calibration models should be reconstructed for different systems and application environments. This study presents an efficient procedure in the construction and selection of calibration models for LIBS analysis. The procedure concludes data preprocess, calibration model construction, and concentration calculation. These steps can be programmed without manual intervention. Results of the quantitative analysis of Ni-based alloys using the proposed procedure are presented in this study.Ten elements are calibrated, and most have an average relative standard error of less than 10%.The proposed procedure is an effective process for constructing and selecting calibration models.展开更多
Lipid-formulated RNA vaccines have been widely used for disease prevention and treatment,yet their mechanism of action and individual components contributing to such actions remain to be delineated.Here,we show that a...Lipid-formulated RNA vaccines have been widely used for disease prevention and treatment,yet their mechanism of action and individual components contributing to such actions remain to be delineated.Here,we show that a therapeutic cancer vaccine composed of a protamine/mRNA core and a lipid shell is highly potent in promoting cytotoxic CD8+T cell responses and mediating anti-tumor immunity.Mechanistically,both the mRNA core and lipid shell are needed to fully stimulate the expression of type I interferons and inflammatory cytokines in dendritic cells.Stimulation of interferon-βexpression is exclusively dependent on STING,and antitumor activity from the mRNA vaccine is significantly compromised in mice with a defective Sting gene.Thus,the mRNA vaccine elicits STING-dependent antitumor immunity.展开更多
Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Recently,few-shot models have been used for Named Entity Recognition(NER).Prototypical network shows high efficie...Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Recently,few-shot models have been used for Named Entity Recognition(NER).Prototypical network shows high efficiency on few-shot NER.However,existing prototypical methods only consider the similarity of tokens in query sets and support sets and ignore the semantic similarity among the sentences which contain these entities.We present a novel model,Few-shot Named Entity Recognition with Joint Token and Sentence Awareness(JTSA),to address the issue.The sentence awareness is introduced to probe the semantic similarity among the sentences.The Token awareness is used to explore the similarity of the tokens.To further improve the robustness and results of the model,we adopt the joint learning scheme on the few-shot NER.Experimental results demonstrate that our model outperforms state-of-the-art models on two standard Fewshot NER datasets.展开更多
Predicting interactions between drugs and target proteins has become an essential task in the drug discovery process.Although the method of validation via wet-lab experiments has become available,experimental methods ...Predicting interactions between drugs and target proteins has become an essential task in the drug discovery process.Although the method of validation via wet-lab experiments has become available,experimental methods for drug-target interaction(DTI)identification remain either time consuming or heavily dependent on domain expertise.Therefore,various computational models have been proposed to predict possible interactions between drugs and target proteins.However,most prediction methods do not consider the topological structures characteristics of the relationship.In this paper,we propose a relational topologybased heterogeneous network embedding method to predict drug-target interactions,abbreviated as RTHNE_DTI.We first construct a heterogeneous information network based on the interaction between different types of nodes,to enhance the ability of association discovery by fully considering the topology of the network.Then drug and target protein nodes can be represented by the other types of nodes.According to the different topological structure of the relationship between the nodes,we divide the relationship in the heterogeneous network into two categories and model them separately.Extensive experiments on the realworld drug datasets,RTHNE_DTI produces high efficiency and outperforms other state-of-the-art methods.RTHNE_DTI can be further used to predict the interaction between unknown interaction drug-target pairs.展开更多
Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Many few-shot models have been widely used for relation learning tasks.However,each of these models has a shortag...Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Many few-shot models have been widely used for relation learning tasks.However,each of these models has a shortage of capturing a certain aspect of semantic features,for example,CNN on long-range dependencies part,Transformer on local features.It is difficult for a single model to adapt to various relation learning,which results in a high variance problem.Ensemble strategy could be competitive in improving the accuracy of few-shot relation extraction and mitigating high variance risks.This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features.Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.展开更多
Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in...Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in the training corpus. In this paper, we propose using co-reference resolution to improve the word embedding by extracting better context. We evaluate four word embeddings with considerations of co-reference resolution and compare the quality of word embedding on the task of word analogy and word similarity on multiple data sets.Experiments show that by using co-reference resolution, the word embedding performance in the word analogy task can be improved by around 1.88%. We find that the words that are names of countries are affected the most,which is as expected.展开更多
基金State Key Program of National Natural Science of China,Grant/Award Number:61533018National Natural Science Foundation of China,Grant/Award Number:61402220+2 种基金Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323Natural Science Foundation of Hunan Province,Grant/Award Number:2020JJ4525Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Numbers:18B279,19A439。
文摘At present,the entity and relation joint extraction task has attracted more and more scholars'attention in the field of natural language processing(NLP).However,most of their methods rely on NLP tools to construct dependency trees to obtain sentence structure information.The adjacency matrix constructed by the dependency tree can convey syntactic information.Dependency trees obtained through NLP tools are too dependent on the tools and may not be very accurate in contextual semantic description.At the same time,a large amount of irrelevant information will cause redundancy.This paper presents a novel end-to-end entity and relation joint extraction based on the multihead attention graph convolutional network model(MAGCN),which does not rely on external tools.MAGCN generates an adjacency matrix through a multi-head attention mechanism to form an attention graph convolutional network model,uses head selection to identify multiple relations,and effectively improve the prediction result of overlapping relations.The authors extensively experiment and prove the method's effectiveness on three public datasets:NYT,WebNLG,and CoNLL04.The results show that the authors’method outperforms the state-of-the-art research results for the task of entities and relation extraction.
基金supported by the National Natural Science Foundation of China(21576154)the Natural Science Foundation of Guangdong Province(2022A1515011999 and 2019A1515011955)the Shenzhen Basic Research Project(20200829101039001 and GXWD20201231165806004)。
文摘Electrode materials with good redox kinetics,excellent mass transfer characteristics and ultra-high stability play a crucial role in reducing the life-cycle cost and prolonging the maintenance-free time of the vanadium flow batteries(VFB).Herein,a nitrogen-doped porous graphite felt electrode(N-PGF)is proposed by growing ZIF-67 nanoparticles on carbon fibers and then calcinating and acid etching.The multi-scale structure of“carbon fiber gap(electrolyte flow),micro/nano pore(active species diffusion)and Nitrogen active center(reaction site)”in N-PGF electrode effectively increases the catalytic sites and promotes mass transfer characteristics.Reasonable electrode design makes the battery show excellent rate performance and ultra-high cycling stability.The peak power density of the battery reaches 1006 mW cm^(-2).During 1000 cycles at 150 mA cm^(-2),the average discharge capacity and average discharge energy of N-PGF increase substantially by 11.6%and 23.4%compared with the benchmark thermal activated graphite felt,respectively.More excitingly,after ultra-long term(5000 cycles)operation at an ultra-high current density(300 mA cm^(-2)),N-PGF exhibits an unprecedented energy efficiency retention(99.79%)and electrochemical performance stability.
基金973 Program,Grant/Award Number:2014CB340504The State Key Program of National Natural Science of China,Grant/Award Number:61533018+3 种基金National Natural Science Foundation of China,Grant/Award Number:61402220The Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323Natural Science Foundation of Hunan Province,Grant/Award Number:2020JJ4525Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Number:18B279,19A439。
文摘Current Chinese event detection methods commonly use word embedding to capture semantic representation,but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence.Based on the simple evaluation,it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation.This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words.This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser.The authors evaluate different models on kbp 2017 corpus.The experimental results show that the proposed method can significantly improve performance in Chinese event detection.
基金financial support provided by National Natural Science Foundation of China (11704372)Anhui Provincial Natural Science Foundation (1708085QF130)
文摘Laser-induced breakdown spectroscopy has become a general-purpose technique, and internal standard calibration is a common method for quantitative analysis. Calibration models should be reconstructed for different systems and application environments. This study presents an efficient procedure in the construction and selection of calibration models for LIBS analysis. The procedure concludes data preprocess, calibration model construction, and concentration calculation. These steps can be programmed without manual intervention. Results of the quantitative analysis of Ni-based alloys using the proposed procedure are presented in this study.Ten elements are calibrated, and most have an average relative standard error of less than 10%.The proposed procedure is an effective process for constructing and selecting calibration models.
基金partially supported with a sponsored research grant from Stemirna Therapeutics,Chinafrom internal funding sources in Houston Methodist Research Institute,USA
文摘Lipid-formulated RNA vaccines have been widely used for disease prevention and treatment,yet their mechanism of action and individual components contributing to such actions remain to be delineated.Here,we show that a therapeutic cancer vaccine composed of a protamine/mRNA core and a lipid shell is highly potent in promoting cytotoxic CD8+T cell responses and mediating anti-tumor immunity.Mechanistically,both the mRNA core and lipid shell are needed to fully stimulate the expression of type I interferons and inflammatory cytokines in dendritic cells.Stimulation of interferon-βexpression is exclusively dependent on STING,and antitumor activity from the mRNA vaccine is significantly compromised in mice with a defective Sting gene.Thus,the mRNA vaccine elicits STING-dependent antitumor immunity.
基金The State Key Program of National Natural Science of China,Grant/Award Number:61533018National Natural Science Foundation of China,Grant/Award Number:61402220+2 种基金The Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323Natural Science Foundation of Hunan Province,Grant/Award Number:2020J4525,2022JJ30495Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Number:18B279,19A439,22A0316.
文摘Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Recently,few-shot models have been used for Named Entity Recognition(NER).Prototypical network shows high efficiency on few-shot NER.However,existing prototypical methods only consider the similarity of tokens in query sets and support sets and ignore the semantic similarity among the sentences which contain these entities.We present a novel model,Few-shot Named Entity Recognition with Joint Token and Sentence Awareness(JTSA),to address the issue.The sentence awareness is introduced to probe the semantic similarity among the sentences.The Token awareness is used to explore the similarity of the tokens.To further improve the robustness and results of the model,we adopt the joint learning scheme on the few-shot NER.Experimental results demonstrate that our model outperforms state-of-the-art models on two standard Fewshot NER datasets.
基金funded by the National Natural Science Foundation of China,grant number 61402220the key program of Scientific Research Fund of Hunan Provincial Education Department,grant number 19A439the Project supported by the Natural Science Foundation of Hunan Province,China,grant number 2020J4525 and grant number 2022J30495.
文摘Predicting interactions between drugs and target proteins has become an essential task in the drug discovery process.Although the method of validation via wet-lab experiments has become available,experimental methods for drug-target interaction(DTI)identification remain either time consuming or heavily dependent on domain expertise.Therefore,various computational models have been proposed to predict possible interactions between drugs and target proteins.However,most prediction methods do not consider the topological structures characteristics of the relationship.In this paper,we propose a relational topologybased heterogeneous network embedding method to predict drug-target interactions,abbreviated as RTHNE_DTI.We first construct a heterogeneous information network based on the interaction between different types of nodes,to enhance the ability of association discovery by fully considering the topology of the network.Then drug and target protein nodes can be represented by the other types of nodes.According to the different topological structure of the relationship between the nodes,we divide the relationship in the heterogeneous network into two categories and model them separately.Extensive experiments on the realworld drug datasets,RTHNE_DTI produces high efficiency and outperforms other state-of-the-art methods.RTHNE_DTI can be further used to predict the interaction between unknown interaction drug-target pairs.
基金The State Key Program of National Natural Science of China,Grant/Award Number:61533018National Natural Science Foundation of China,Grant/Award Number:61402220+2 种基金The Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323Natural Science Foundation of Hunan Province,Grant/Award Number:2020JJ4525,2022JJ30495Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Number:18B279,19A439
文摘Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Many few-shot models have been widely used for relation learning tasks.However,each of these models has a shortage of capturing a certain aspect of semantic features,for example,CNN on long-range dependencies part,Transformer on local features.It is difficult for a single model to adapt to various relation learning,which results in a high variance problem.Ensemble strategy could be competitive in improving the accuracy of few-shot relation extraction and mitigating high variance risks.This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features.Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.
基金supported by the National HighTech Research and Development(863)Program(No.2015AA015401)the National Natural Science Foundation of China(Nos.61533018 and 61402220)+2 种基金the State Scholarship Fund of CSC(No.201608430240)the Philosophy and Social Science Foundation of Hunan Province(No.16YBA323)the Scientific Research Fund of Hunan Provincial Education Department(Nos.16C1378 and 14B153)
文摘Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in the training corpus. In this paper, we propose using co-reference resolution to improve the word embedding by extracting better context. We evaluate four word embeddings with considerations of co-reference resolution and compare the quality of word embedding on the task of word analogy and word similarity on multiple data sets.Experiments show that by using co-reference resolution, the word embedding performance in the word analogy task can be improved by around 1.88%. We find that the words that are names of countries are affected the most,which is as expected.