Dialogue State Tracking(DST)is a critical component of task-oriented spoken dialogue systems(SDS),tasked with maintaining an accurate representation of the conversational state by predicting slots and their correspond...Dialogue State Tracking(DST)is a critical component of task-oriented spoken dialogue systems(SDS),tasked with maintaining an accurate representation of the conversational state by predicting slots and their corresponding values.Recent advances leverage Large Language Models(LLMs)with prompt-based tuning to improve tracking accuracy and efficiency.However,these approaches often incur substantial computational and memory overheads and typically address slot extraction implicitly within prompts,without explicitly modeling the complex dependencies between slots and values.In this work,we propose PUGG,a novel DST framework that constructs schema-driven prompts to fine-tune GPT-2 and utilizes its tokenizer to implement a memory encoder.PUGG explicitly extracts slot values via GPT-2 and employs Graph Attention Networks(GATs)to model and reason over the intricate relationships between slots and their associated values.We evaluate PUGG on four publicly available datasets,where it achieves stateof-the-art performance across multiple evaluation metrics,highlighting its robustness and generalizability in diverse conversational scenarios.Our results indicate that the integration of GPT-2 substantially reduces model complexity and memory consumption by streamlining key processes.Moreover,prompt tuning enhances the model’s flexibility and precision in extracting relevant slot-value pairs,while the incorporation of GATs facilitates effective relational reasoning,leading to improved dialogue state representations.展开更多
The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.A...The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.Although the features of the first 2^(+)excited states can be measured for stable nuclei and calculated using nuclear models,significant uncertainty remains.This study employs a machine learning model based on a light gradient boosting machine(LightGBM)to investigate the first 2^(+)excited states.Specifically,the training of the LightGBM algorithm and the prediction of the first 2^(+)properties of 642 nuclei are presented.Furthermore,detailed comparisons of the LightGBM predictions were performed with available experimental data,shell model calculations,and Bayesian neural network predictions.The results revealed that the average difference between the LightGBM predictions and the experimental data was 18 times smaller than that obtained by the shell model and only 70%of the BNN prediction results.Considering Mg,Ca,Kr,Sm,and Pb isotopes as examples,it was also observed that LightGBM can effectively reproduce the magic number mutation caused by shell effects,with the energy being as low as 0.04 MeV due to shape coexistence.Therefore,we believe that leveraging LightGBM-based machine learning can profoundly enhance our insights into nuclear structures and provide new avenues for nuclear physics research.展开更多
Electrocatalytic CO_(2) reduction(ECR)is a promising approach for achieving carbon neutrality due to its ability to convert CO_(2) to valuable chemicals.Recent advances have significantly enhanced the ECR performance ...Electrocatalytic CO_(2) reduction(ECR)is a promising approach for achieving carbon neutrality due to its ability to convert CO_(2) to valuable chemicals.Recent advances have significantly enhanced the ECR performance of various catalysts by tuning their oxidation states,particularly for Cu-based catalysts that can reduce CO_(2) to multiple products.However,the oxidation state of copper(OSCu),especially Cu+,changes during the reaction process,posing significant challenges for both catalyst characterization and performance.In this review,the current understanding of the effect of oxidation states on product selectivity was first discussed.A comprehensive overview of in situ/operando characterization techniques,used to monitor the dynamic evolution of oxidation states during ECR,was then provided.Various strategies for stabilizing oxidation states through modification of catalysts and manipulation of external conditions were discussed.This review aimed to deepen the understanding of oxidation states in ECR and enlighten the development of more efficient electrocatalysts.展开更多
Herein,we established a Zn_(3)(OH)_(2)(V_(2)O_(7))(H_(2)O)_(2)/V-Zn(O,S)Z-scheme heterojunction labeled ZnVO/V-Zn(O,S)with a heterovalent V^(4+)/V^(5+)states and oxygen vacancies in both phases via a one-step in-situ ...Herein,we established a Zn_(3)(OH)_(2)(V_(2)O_(7))(H_(2)O)_(2)/V-Zn(O,S)Z-scheme heterojunction labeled ZnVO/V-Zn(O,S)with a heterovalent V^(4+)/V^(5+)states and oxygen vacancies in both phases via a one-step in-situ hydrolysis method.The NaBH_(4) regulated the ZnVO/V-Zn(O,S)-3 with rich Vo and suitable n(V^(4+))/n(V^(5+))ratio achieved an excellent photocatalytic nitrogen fixation activity of 301.7μmol/(g×h)and apparent quantum efficiency of 1.148%at 420 nm without any sacrificial agent,which is 11 times than that of V-Zn(O,S).The Vo acts as the active site to trap and activate N_(2) molecules and to trap and activate H_(2)O to produce the H for N_(2) molecules photocatalytic reduction.The rich Vo defects can also reduce the competitive adsorption of H_(2)O and N_(2) molecules on the surface active site of the catalyst.The heterovalent vanadium states act as the photogenerated electrons,quickly hopping between V^(4+)and V^(5+)to transfer for the photocatalytic N_(2) reduction reaction.Additionally,the Z-scheme heterojunction effectively minimizes photogenerated carrier recombination.These synergistic effects collectively boost the photocatalytic nitrogen fixation activity.This study provides a practical method for designing Z-scheme heterojunctions for efficient photocatalytic N_(2) fixation under mild conditions.展开更多
Objective Sepsis patients exhibit diverse immune states,making it crucial to identify subtypes with distinct inflammatory profiles through Th1/Th2 cytokine data for personalized treatment and improved prognosis.Method...Objective Sepsis patients exhibit diverse immune states,making it crucial to identify subtypes with distinct inflammatory profiles through Th1/Th2 cytokine data for personalized treatment and improved prognosis.Methods We retrieved data from sepsis patients who underwent Th1/Th2 cytokine testing in Nanfang Hospital,Southern Medical University from June 1,2020,to February 1,2022.An unsupervised K-means clustering method classified participants based on Th1/Th2 cytokine levels,with the primary outcome being the 7-day mortality rate post-ICU admission.Cox proportional hazards and Restricted Mean Survival Time(RMST)analyses were utilized to explore survival outcomes.Results A total of 321 sepsis patients were included.IL-6(HR 1.69,95%CI:1.22,2.34)and IL-10(HR 1.81,95%CI:1.37,2.40)emerged as independent predictors of 7-day mortality.Unsupervised K-means clustering revealed 3 inflammatory/immune subgroups:Cluster 1(n=166,low inflammatory response),Cluster 2(n=99,moderate inflammatory response with immune suppression),and Cluster 3(n=56,strong inflammatory and immune suppression).Compared to Cluster 1,Clusters 2 and 3 had higher 7-day mortality risks(14.4%vs 23.2%,HR=4.30,95%CI:1.51-12.26;14.4%vs 35.7%,HR=7.32,95%CI:2.57-20.79).Conclusion Septic patients in a protective immune response state(Cluster 1)exhibit better short-term prognoses,suggesting the importance of understanding inflammatory/immune states for precise treatment and improved outcomes.展开更多
Photothermal synergistic catalytic systems for treating volatile organic compounds(VOCs)have attracted signif-icant attention due to their energy efficiency and potential to reduce carbon emissions.However,the mechani...Photothermal synergistic catalytic systems for treating volatile organic compounds(VOCs)have attracted signif-icant attention due to their energy efficiency and potential to reduce carbon emissions.However,the mechanism underlying the synergistic reaction remains a critical issue.This study introduces a photothermal synergistic system for the removal of ethyl acetate(EA)by synthesizing Cu-doped OMS-2(denoted as Cu-OMS-2).Under ultraviolet-visible(UV–Vis)irradiation in a flow system,the Cu-OMS-2 catalyst exhibited significantly enhanced performance in the EA degradation process,nearly doubling the effectiveness of pure OMS-2,and increasing carbon dioxide yield by 20%.This exceptional performance is attributed to the synergistic effect of increased oxygen vacancies(OV)at OMS-2 active sites and Cu doping,as confirmed by H2-TPR,O_(2)-TPD,and CO consump-tion measurements.This study clarifies the catalytic mechanism of light-assisted thermocatalysis and offers a novel strategy for designing photothermal catalysts with homogeneous Cu-doped nanorods for VOC removal.展开更多
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the ITRC(Information Technology Research Centre)support program(IITP-2024-RS-2024-00437191)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation).
文摘Dialogue State Tracking(DST)is a critical component of task-oriented spoken dialogue systems(SDS),tasked with maintaining an accurate representation of the conversational state by predicting slots and their corresponding values.Recent advances leverage Large Language Models(LLMs)with prompt-based tuning to improve tracking accuracy and efficiency.However,these approaches often incur substantial computational and memory overheads and typically address slot extraction implicitly within prompts,without explicitly modeling the complex dependencies between slots and values.In this work,we propose PUGG,a novel DST framework that constructs schema-driven prompts to fine-tune GPT-2 and utilizes its tokenizer to implement a memory encoder.PUGG explicitly extracts slot values via GPT-2 and employs Graph Attention Networks(GATs)to model and reason over the intricate relationships between slots and their associated values.We evaluate PUGG on four publicly available datasets,where it achieves stateof-the-art performance across multiple evaluation metrics,highlighting its robustness and generalizability in diverse conversational scenarios.Our results indicate that the integration of GPT-2 substantially reduces model complexity and memory consumption by streamlining key processes.Moreover,prompt tuning enhances the model’s flexibility and precision in extracting relevant slot-value pairs,while the incorporation of GATs facilitates effective relational reasoning,leading to improved dialogue state representations.
基金supported by the National Key R&D Program of China (No. 2022YFA1603300)the Romanian Ministry of Research,Innovation and Digitalization under Contract PN 23.21.01.06+1 种基金The ELI-RO project with Contract ELI-RORDI-2024-008 (AMAP)a grant from the Romanian Ministry of Research,Innovation and Digitization,CNCS-UEFIS-CDI,with project numbers PN-Ⅲ-P4-PCE-2021-1014, PN-Ⅲ-P4-PCE-2021-0595, and PN-Ⅲ-P1-1.1-TE2021-1464 within PNCDI Ⅲ
文摘The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.Although the features of the first 2^(+)excited states can be measured for stable nuclei and calculated using nuclear models,significant uncertainty remains.This study employs a machine learning model based on a light gradient boosting machine(LightGBM)to investigate the first 2^(+)excited states.Specifically,the training of the LightGBM algorithm and the prediction of the first 2^(+)properties of 642 nuclei are presented.Furthermore,detailed comparisons of the LightGBM predictions were performed with available experimental data,shell model calculations,and Bayesian neural network predictions.The results revealed that the average difference between the LightGBM predictions and the experimental data was 18 times smaller than that obtained by the shell model and only 70%of the BNN prediction results.Considering Mg,Ca,Kr,Sm,and Pb isotopes as examples,it was also observed that LightGBM can effectively reproduce the magic number mutation caused by shell effects,with the energy being as low as 0.04 MeV due to shape coexistence.Therefore,we believe that leveraging LightGBM-based machine learning can profoundly enhance our insights into nuclear structures and provide new avenues for nuclear physics research.
基金supported by the National Natural Science Foundation of China(No.52221004)the Shenzhen Science and Technology Program(No.RCJC20221008092758099)+1 种基金the Shenzhen Pengrui Young Faculty Program of Shenzhen Pengrui Foundation(No.SZPR2023004)the Guangdong Higher Education Institutions Innovative Research Team of Urban Water Cycle and Ecological Safety(No.2023KCXTD053).
文摘Electrocatalytic CO_(2) reduction(ECR)is a promising approach for achieving carbon neutrality due to its ability to convert CO_(2) to valuable chemicals.Recent advances have significantly enhanced the ECR performance of various catalysts by tuning their oxidation states,particularly for Cu-based catalysts that can reduce CO_(2) to multiple products.However,the oxidation state of copper(OSCu),especially Cu+,changes during the reaction process,posing significant challenges for both catalyst characterization and performance.In this review,the current understanding of the effect of oxidation states on product selectivity was first discussed.A comprehensive overview of in situ/operando characterization techniques,used to monitor the dynamic evolution of oxidation states during ECR,was then provided.Various strategies for stabilizing oxidation states through modification of catalysts and manipulation of external conditions were discussed.This review aimed to deepen the understanding of oxidation states in ECR and enlighten the development of more efficient electrocatalysts.
文摘Herein,we established a Zn_(3)(OH)_(2)(V_(2)O_(7))(H_(2)O)_(2)/V-Zn(O,S)Z-scheme heterojunction labeled ZnVO/V-Zn(O,S)with a heterovalent V^(4+)/V^(5+)states and oxygen vacancies in both phases via a one-step in-situ hydrolysis method.The NaBH_(4) regulated the ZnVO/V-Zn(O,S)-3 with rich Vo and suitable n(V^(4+))/n(V^(5+))ratio achieved an excellent photocatalytic nitrogen fixation activity of 301.7μmol/(g×h)and apparent quantum efficiency of 1.148%at 420 nm without any sacrificial agent,which is 11 times than that of V-Zn(O,S).The Vo acts as the active site to trap and activate N_(2) molecules and to trap and activate H_(2)O to produce the H for N_(2) molecules photocatalytic reduction.The rich Vo defects can also reduce the competitive adsorption of H_(2)O and N_(2) molecules on the surface active site of the catalyst.The heterovalent vanadium states act as the photogenerated electrons,quickly hopping between V^(4+)and V^(5+)to transfer for the photocatalytic N_(2) reduction reaction.Additionally,the Z-scheme heterojunction effectively minimizes photogenerated carrier recombination.These synergistic effects collectively boost the photocatalytic nitrogen fixation activity.This study provides a practical method for designing Z-scheme heterojunctions for efficient photocatalytic N_(2) fixation under mild conditions.
文摘Objective Sepsis patients exhibit diverse immune states,making it crucial to identify subtypes with distinct inflammatory profiles through Th1/Th2 cytokine data for personalized treatment and improved prognosis.Methods We retrieved data from sepsis patients who underwent Th1/Th2 cytokine testing in Nanfang Hospital,Southern Medical University from June 1,2020,to February 1,2022.An unsupervised K-means clustering method classified participants based on Th1/Th2 cytokine levels,with the primary outcome being the 7-day mortality rate post-ICU admission.Cox proportional hazards and Restricted Mean Survival Time(RMST)analyses were utilized to explore survival outcomes.Results A total of 321 sepsis patients were included.IL-6(HR 1.69,95%CI:1.22,2.34)and IL-10(HR 1.81,95%CI:1.37,2.40)emerged as independent predictors of 7-day mortality.Unsupervised K-means clustering revealed 3 inflammatory/immune subgroups:Cluster 1(n=166,low inflammatory response),Cluster 2(n=99,moderate inflammatory response with immune suppression),and Cluster 3(n=56,strong inflammatory and immune suppression).Compared to Cluster 1,Clusters 2 and 3 had higher 7-day mortality risks(14.4%vs 23.2%,HR=4.30,95%CI:1.51-12.26;14.4%vs 35.7%,HR=7.32,95%CI:2.57-20.79).Conclusion Septic patients in a protective immune response state(Cluster 1)exhibit better short-term prognoses,suggesting the importance of understanding inflammatory/immune states for precise treatment and improved outcomes.
基金supported by the Qilu University of Technology(Shandong Academy of Sciences),the Basic Research Project of Science,Education and Industry Integration Pilot Project(No.2022PY047).
文摘Photothermal synergistic catalytic systems for treating volatile organic compounds(VOCs)have attracted signif-icant attention due to their energy efficiency and potential to reduce carbon emissions.However,the mechanism underlying the synergistic reaction remains a critical issue.This study introduces a photothermal synergistic system for the removal of ethyl acetate(EA)by synthesizing Cu-doped OMS-2(denoted as Cu-OMS-2).Under ultraviolet-visible(UV–Vis)irradiation in a flow system,the Cu-OMS-2 catalyst exhibited significantly enhanced performance in the EA degradation process,nearly doubling the effectiveness of pure OMS-2,and increasing carbon dioxide yield by 20%.This exceptional performance is attributed to the synergistic effect of increased oxygen vacancies(OV)at OMS-2 active sites and Cu doping,as confirmed by H2-TPR,O_(2)-TPD,and CO consump-tion measurements.This study clarifies the catalytic mechanism of light-assisted thermocatalysis and offers a novel strategy for designing photothermal catalysts with homogeneous Cu-doped nanorods for VOC removal.
