In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challen...In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challenging task. However, previous work has primarily focused on the independent recognition of user intent and emotion, making it difficult to simultaneously track both aspects in the dialogue tracking module and to effectively utilize user emotions in subsequent dialogue strategies. We propose a Multi-Head Encoder Shared Model (MESM) that dynamically integrates features from emotion and intent encoders through a feature fusioner. Addressing the scarcity of datasets containing both emotion and intent labels, we designed a multi-dataset learning approach enabling the model to generate dialogue summaries encompassing both user intent and emotion. Experiments conducted on the MultiWoZ and MELD datasets demonstrate that our model effectively captures user intent and emotion, achieving extremely competitive results in dialogue state tracking tasks.展开更多
The Fourth Dialogue on Exchanges and Mutual Learning Among Civilisations was held in Dunhuang in Northwest China's Gansu Province on Friday,bringing together politicians,heads of international organisations,schola...The Fourth Dialogue on Exchanges and Mutual Learning Among Civilisations was held in Dunhuang in Northwest China's Gansu Province on Friday,bringing together politicians,heads of international organisations,scholars and experts to discuss the significance of exchanges and dialogues between different civilisations in a world facing many conflicts.展开更多
Oral expression skills play an essential role in the development of EFL students’language abilities,and how to improve EFL students’oral expression skills is an essential and challenging task.This study adopts a qua...Oral expression skills play an essential role in the development of EFL students’language abilities,and how to improve EFL students’oral expression skills is an essential and challenging task.This study adopts a quasi-experimental research method to carry out the research and proposes an AI-based reflective dialogue model.Based on this,an analysis of the impact brought by this model on EFL students’oral expression performance and learning anxiety levels.The results show that students in the experimental group have significantly higher oral expression performance than those in the control group in the three dimensions of grammatical accuracy,expressive fluency,and word accuracy.In addition,the students in the experimental group produced facilitated anxiety after using the AI-based reflective dialogue model for oral expression learning,which prompted the students to learn more diligently.展开更多
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
Agroup of young representatives and scholars from more than 10 foreign countries had great fun collecting water samples from the Grand Canal in Sanwan Park,Yangzhou City,east China’s Jiangsu Province,on June 3,2025.T...Agroup of young representatives and scholars from more than 10 foreign countries had great fun collecting water samples from the Grand Canal in Sanwan Park,Yangzhou City,east China’s Jiangsu Province,on June 3,2025.The samples were poured into a“pot of civilization,”which symbolized the integration of cultures.In addition to the canal,the young people also visited places such as Yangzhou University,China Grand Canal Museum,and the Slender West Lake,learning the culture of the Grand Canal and the canal city of Yangzhou.展开更多
France’s Barbizon School of art finds commonalities in China’s landscape painting and rural art,showcasing the universality of creativity.THE village of Barbizon in north-cenral France,located on the outskirts of th...France’s Barbizon School of art finds commonalities in China’s landscape painting and rural art,showcasing the universality of creativity.THE village of Barbizon in north-cenral France,located on the outskirts of the stunning Fontainebleu Forest,became famous in art history for giving rise to a school of painting that sought realism in nature painting,based on deep observation and love for nature.Lishui is a city in Zhejiang Province in east China known as the green valley due to its extensive forest cover.Today,it has also become a channel of intercultural dialogue between China and France.展开更多
On 28 November 2024,the Chinese Association for International Understanding(CAFIU)hosted the Dialogue on Mutual Learning between Chinese and German Civilisations in Berlin,Germany.Ji Bingxuan,Vice-Chairperson of the S...On 28 November 2024,the Chinese Association for International Understanding(CAFIU)hosted the Dialogue on Mutual Learning between Chinese and German Civilisations in Berlin,Germany.Ji Bingxuan,Vice-Chairperson of the Standing Committee of the 13th National People's Congress of China and President of CAFIU,who was on a visit in Germany,attended the Dialogue and delivered a keynote speech.展开更多
Flipped is a book written by American author Wendelin Van Draanen. It is a novel about young teenagers and was adapted into the famous film of the same name in 2010. The thesis employs speech acts, as pioneered by Joh...Flipped is a book written by American author Wendelin Van Draanen. It is a novel about young teenagers and was adapted into the famous film of the same name in 2010. The thesis employs speech acts, as pioneered by John Austin and further developed by John Searle, to investigate the influence of dialogues on characterization and plot development in Flipped. By exploring the theory of speech acts presented in dialogues between characters, the author deciphers the underlying intentions embodied in the dialogues and demonstrates the importance of the use of speech acts in dialogues in revealing the characters, driving the development of the plot and expressing the theme of the text.展开更多
On the afternoon of May 30,the parallel forum"Global Dialogue on Civilisational Inheritance and the Digital Silk Road,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was hel...On the afternoon of May 30,the parallel forum"Global Dialogue on Civilisational Inheritance and the Digital Silk Road,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was held in Dunhuang.The forum focused on key areas of Silk Road civilisation studies in the new era under the theme"Carrying Forward the Silk Road Spirit and Pooling Strength for the Implementation of the Global Civilisation Initiative."Discussions centred on topics such as humanistic research on the Digital Silk Road,translation studies of cultural heritage,and archaeological studies of Silk Road sites,providing a platform for experts and scholars to exchange ideas and share achievements,and working to build a strong synergy for exchanges and mutual learning among civilisations.展开更多
On the evening of May 30th,the parallel forum"Youth Power in Dialogue among Civilisations,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was held in Dunhuang.The forum was ...On the evening of May 30th,the parallel forum"Youth Power in Dialogue among Civilisations,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was held in Dunhuang.The forum was hosted by the Chinese Association for International Understanding and organised by the Schwarzman College of Tsinghua University.More than 30 youth representatives from the Schwarzman Scholars international delegation and a delegation of European,American and African NGO friends came together under the theme"The Youth Power of Cross-Civilisation Dialogue.Discussions focused on topics such as cultural inheritance and innovation,and cross-cultural collaboration.The sessions were co-chaired by Professor Pan Qingzhong,Executive Dean of the Schwarzman College,and Joshua Woodard,a Schwarzman Scholar from the United States of America.展开更多
In June 2024,the 78th session of the United Nations General Assembly unanimously adopted a resolution proposed by China,designating June 10 of each year as the International Day for Dialogue Among Civilizations.This i...In June 2024,the 78th session of the United Nations General Assembly unanimously adopted a resolution proposed by China,designating June 10 of each year as the International Day for Dialogue Among Civilizations.This initiative aimed to deepen global appreciation for the value of civilizational diversity,promote dialogue and mutual respect,and advance the construction of a more harmonious and interconnected world.展开更多
At the invitation of the Economic,Social and Cultural Council(ECOSOCC)of the African Union,Li Jun,Vice-President of China NGO Network for International Exchanges(CNIE)and former Vice-Minister of the International Depa...At the invitation of the Economic,Social and Cultural Council(ECOSOCC)of the African Union,Li Jun,Vice-President of China NGO Network for International Exchanges(CNIE)and former Vice-Minister of the International Department of the CPC Central Committee,led a six-member delegation to Zambia from May 7th to 9th to attend the Africa-China People-to-People Dialogue.The event brought together over 150 participants,including Han Jing,Chinese Ambassador to Zambia and representatives from all walks of life in China and Africa.展开更多
In late May,the city of Dunhuang,a key historical hub of Eastern and Western cultures in Northwest China's Gansu Province,basked in clear and refreshing weather under a brilliant blue sky.The rugged Mingsha Mounta...In late May,the city of Dunhuang,a key historical hub of Eastern and Western cultures in Northwest China's Gansu Province,basked in clear and refreshing weather under a brilliant blue sky.The rugged Mingsha Mountain,renowned for the musical sounds produced by wind-blown sands when the wind blows,stood in silent majesty.To the close north of the mountain's massive golden dunes stood the city's international convention centre,where some 400 vips from 60 countries host cultural exchanges and mutual learning.展开更多
Ⅰ.We,political party leaders,government ministers and representatives of various sectors from over 140 countries held the Global Civilizations Dialogue Ministerial Meeting from 10 to 11 July 2025 in Beijing,China.Foc...Ⅰ.We,political party leaders,government ministers and representatives of various sectors from over 140 countries held the Global Civilizations Dialogue Ministerial Meeting from 10 to 11 July 2025 in Beijing,China.Focusing on the theme Safeguarding Diversity of Human Civilizations for World Peace and Development,we engaged in in-depth exchanges and reached broad consensus.展开更多
Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to...Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to explore a pre-training paradigm for CI-ToD.Nevertheless,pre-training for CI-ToD is non-trivial because it requires a large amount of multi-turn KB-grounded dialogues,which are extremely hard to collect.To alleviate the data scarcity problem for pre-training,we introduce a modularized pre-training framework(MPFToD),which is capable of utilizing large amounts of KB-free dialogues.Specifically,such modularization allows us to decouple CI-ToD into three sub-modules and propose three pre-training tasks including(i)query response matching pre-training;(ii)dialogue history consistent identification pre-training;and(iii)KB mask language modeling to enhance different abilities of CI-ToD model.As different sub-tasks are solved separately,MPFToD can learn from large amounts of KB-free dialogues for different modules,which are much easier to obtain.Results on the CI-ToD benchmark show that MPFToD pushes the state-of-the-art performance from 56.3%to 61.0%.Furthermore,we show its transferability with promising performance on other downstream tasks(i.e.,dialog act recognition,sentiment classification and table fact checking).展开更多
Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low informatio...Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low information density in dialogues,methods based on trigger enhancement have been proposed,yielding positive results.However,trigger enhancement faces challenges,which cause suboptimal model performance.First,the proportion of annotated triggers is low in DialogRE.Second,feature representations of triggers and arguments often contain conflicting information.In this paper,we propose a novel Multi-Feature Filtering and Fusion trigger enhancement approach to overcome these limitations.We first obtain representations of arguments,and triggers that contain rich semantic information through attention and gate methods.Then,we design a feature filtering mechanism that eliminates conflicting features in the encoding of trigger prototype representations and their corresponding argument pairs.Additionally,we utilize large language models to create prompts based on Chain-of-Thought and In-context Learning for automated trigger extraction.Experiments show that our model increases the average F1 score by 1.3%in the dialogue relation extraction task.Ablation and case studies confirm the effectiveness of our model.Furthermore,the feature filtering method effectively integrates with other trigger enhancement models,enhancing overall performance and demonstrating its ability to resolve feature conflicts.展开更多
Quantum dialogue(QD)realizes the real-time secure bidirectional quantum communication.Measurement-deviceindependent(MDI)QD can resist all possible attacks focusing on the imperfect measurement devices and enhance QD’...Quantum dialogue(QD)realizes the real-time secure bidirectional quantum communication.Measurement-deviceindependent(MDI)QD can resist all possible attacks focusing on the imperfect measurement devices and enhance QD’s practical security.However,in practical applications,any secure communication requires identity authentication as a prerequisite.In this paper,we propose an MDI QD protocol with bidirectional identity authentication.The practical communication parties can first authenticate the identity of each other simultaneously before the message exchange.In theory,our MDI QD protocol has unconditional security and the communication parties can exchange 1.5 bits of messages in each communication round with linear optical Bell state measurement.We numerically simulate the secrecy message capacity of our MDI QD protocol.Our protocol has two advantages.First,it can effectively resist the impersonation attack and enhance MDI QD’s practical security.Second,it does not require keys to assist the message exchange and has relatively high efficiency.Our protocol has application potential in the future quantum communication field.展开更多
At a time when humanity grapples with intersecting deficits in peace,development,security and governance,civilizations stand at a crossroads.As traditional Western-led solutions falter,China’s Global Civilization Ini...At a time when humanity grapples with intersecting deficits in peace,development,security and governance,civilizations stand at a crossroads.As traditional Western-led solutions falter,China’s Global Civilization Initiative(GCI)emerges as a transformative framework,translating historical wisdom into actionable strategies.Recent forums like the 11th Nishan Forum on World Civilizations and the Global Civilizations Dialogue Ministerial Meeting underscore growing consensus on core principles:equality,mutual learning,inclusive dialogue,and collaborative response to global challenges.As Chinese President Xi Jinping pointed out in his congratulatory letter to the Global Civilizations Dialogue Ministerial Meeting,“History shows that exchanges and mutual learning among civilizations are essential for civilizations to flourish and for human progress to be made.”展开更多
Quantum dialogue(QD)enables two communication parties to directly exchange secret messages simultaneously.In conventional QD protocols,photons need to transmit in the quantum channel for two rounds.In this paper,we pr...Quantum dialogue(QD)enables two communication parties to directly exchange secret messages simultaneously.In conventional QD protocols,photons need to transmit in the quantum channel for two rounds.In this paper,we propose a one-step QD protocol based on the hyperentanglement.With the help of the non-local hyperentanglement-assisted Bell state measurement(BSM),the photons only need to transmit in the quantum channel once.We prove that our one-step QD protocol is secure in theory and numerically simulate its secret message capacity under practical experimental condition.Compared with previous QD protocols,the one-step QD protocol can effectively simplify the experiment operations and reduce the message loss caused by the photon transmission loss.Meanwhile,the non-local hyperentanglement-assisted BSM has a success probability of 100%and is feasible with linear optical elements.Moreover,combined with the hyperentanglement heralded amplification and purification,our protocol is possible to realize long-distance one-step QD.展开更多
The"Decoding Zhonghua"International Conference on Dialogue among Civilisations,hosted by China International Public Relations Association,China Ethnic News and Academy of Contemporary China and World Studies...The"Decoding Zhonghua"International Conference on Dialogue among Civilisations,hosted by China International Public Relations Association,China Ethnic News and Academy of Contemporary China and World Studies was held in Beijing on January 17th.With the theme"Pursing Harmonious Coexistence of Civilisations through Dialogue".展开更多
基金funded by the Science and Technology Foundation of Chongqing EducationCommission(GrantNo.KJQN202301153)the ScientificResearch Foundation of Chongqing University of Technology(Grant No.2021ZDZ025)the Postgraduate Innovation Foundation of Chongqing University of Technology(Grant No.gzlcx20243524).
文摘In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challenging task. However, previous work has primarily focused on the independent recognition of user intent and emotion, making it difficult to simultaneously track both aspects in the dialogue tracking module and to effectively utilize user emotions in subsequent dialogue strategies. We propose a Multi-Head Encoder Shared Model (MESM) that dynamically integrates features from emotion and intent encoders through a feature fusioner. Addressing the scarcity of datasets containing both emotion and intent labels, we designed a multi-dataset learning approach enabling the model to generate dialogue summaries encompassing both user intent and emotion. Experiments conducted on the MultiWoZ and MELD datasets demonstrate that our model effectively captures user intent and emotion, achieving extremely competitive results in dialogue state tracking tasks.
文摘The Fourth Dialogue on Exchanges and Mutual Learning Among Civilisations was held in Dunhuang in Northwest China's Gansu Province on Friday,bringing together politicians,heads of international organisations,scholars and experts to discuss the significance of exchanges and dialogues between different civilisations in a world facing many conflicts.
基金2024 Provincial Teaching Reform Program for Graduate Students in the Second Batch of the 14th Five-Year Plan of Zhejiang Provincial Office of Education:Innovation and Practice of“Six Synergistic”Graduate Teaching Guided by Educator’s Spirit(No.JGCG2024406)Key Project of Zhejiang Provincial Education Science Planning:Research on an interdisciplinary teaching model to promote students’computational thinking from multiple analytical perspectives[No.2025SB103].
文摘Oral expression skills play an essential role in the development of EFL students’language abilities,and how to improve EFL students’oral expression skills is an essential and challenging task.This study adopts a quasi-experimental research method to carry out the research and proposes an AI-based reflective dialogue model.Based on this,an analysis of the impact brought by this model on EFL students’oral expression performance and learning anxiety levels.The results show that students in the experimental group have significantly higher oral expression performance than those in the control group in the three dimensions of grammatical accuracy,expressive fluency,and word accuracy.In addition,the students in the experimental group produced facilitated anxiety after using the AI-based reflective dialogue model for oral expression learning,which prompted the students to learn more diligently.
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.
文摘Agroup of young representatives and scholars from more than 10 foreign countries had great fun collecting water samples from the Grand Canal in Sanwan Park,Yangzhou City,east China’s Jiangsu Province,on June 3,2025.The samples were poured into a“pot of civilization,”which symbolized the integration of cultures.In addition to the canal,the young people also visited places such as Yangzhou University,China Grand Canal Museum,and the Slender West Lake,learning the culture of the Grand Canal and the canal city of Yangzhou.
文摘France’s Barbizon School of art finds commonalities in China’s landscape painting and rural art,showcasing the universality of creativity.THE village of Barbizon in north-cenral France,located on the outskirts of the stunning Fontainebleu Forest,became famous in art history for giving rise to a school of painting that sought realism in nature painting,based on deep observation and love for nature.Lishui is a city in Zhejiang Province in east China known as the green valley due to its extensive forest cover.Today,it has also become a channel of intercultural dialogue between China and France.
文摘On 28 November 2024,the Chinese Association for International Understanding(CAFIU)hosted the Dialogue on Mutual Learning between Chinese and German Civilisations in Berlin,Germany.Ji Bingxuan,Vice-Chairperson of the Standing Committee of the 13th National People's Congress of China and President of CAFIU,who was on a visit in Germany,attended the Dialogue and delivered a keynote speech.
文摘Flipped is a book written by American author Wendelin Van Draanen. It is a novel about young teenagers and was adapted into the famous film of the same name in 2010. The thesis employs speech acts, as pioneered by John Austin and further developed by John Searle, to investigate the influence of dialogues on characterization and plot development in Flipped. By exploring the theory of speech acts presented in dialogues between characters, the author deciphers the underlying intentions embodied in the dialogues and demonstrates the importance of the use of speech acts in dialogues in revealing the characters, driving the development of the plot and expressing the theme of the text.
文摘On the afternoon of May 30,the parallel forum"Global Dialogue on Civilisational Inheritance and the Digital Silk Road,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was held in Dunhuang.The forum focused on key areas of Silk Road civilisation studies in the new era under the theme"Carrying Forward the Silk Road Spirit and Pooling Strength for the Implementation of the Global Civilisation Initiative."Discussions centred on topics such as humanistic research on the Digital Silk Road,translation studies of cultural heritage,and archaeological studies of Silk Road sites,providing a platform for experts and scholars to exchange ideas and share achievements,and working to build a strong synergy for exchanges and mutual learning among civilisations.
文摘On the evening of May 30th,the parallel forum"Youth Power in Dialogue among Civilisations,"as part of the 4th Dialogue on Exchanges and Mutual Learning among Civilisations,was held in Dunhuang.The forum was hosted by the Chinese Association for International Understanding and organised by the Schwarzman College of Tsinghua University.More than 30 youth representatives from the Schwarzman Scholars international delegation and a delegation of European,American and African NGO friends came together under the theme"The Youth Power of Cross-Civilisation Dialogue.Discussions focused on topics such as cultural inheritance and innovation,and cross-cultural collaboration.The sessions were co-chaired by Professor Pan Qingzhong,Executive Dean of the Schwarzman College,and Joshua Woodard,a Schwarzman Scholar from the United States of America.
文摘In June 2024,the 78th session of the United Nations General Assembly unanimously adopted a resolution proposed by China,designating June 10 of each year as the International Day for Dialogue Among Civilizations.This initiative aimed to deepen global appreciation for the value of civilizational diversity,promote dialogue and mutual respect,and advance the construction of a more harmonious and interconnected world.
文摘At the invitation of the Economic,Social and Cultural Council(ECOSOCC)of the African Union,Li Jun,Vice-President of China NGO Network for International Exchanges(CNIE)and former Vice-Minister of the International Department of the CPC Central Committee,led a six-member delegation to Zambia from May 7th to 9th to attend the Africa-China People-to-People Dialogue.The event brought together over 150 participants,including Han Jing,Chinese Ambassador to Zambia and representatives from all walks of life in China and Africa.
文摘In late May,the city of Dunhuang,a key historical hub of Eastern and Western cultures in Northwest China's Gansu Province,basked in clear and refreshing weather under a brilliant blue sky.The rugged Mingsha Mountain,renowned for the musical sounds produced by wind-blown sands when the wind blows,stood in silent majesty.To the close north of the mountain's massive golden dunes stood the city's international convention centre,where some 400 vips from 60 countries host cultural exchanges and mutual learning.
文摘Ⅰ.We,political party leaders,government ministers and representatives of various sectors from over 140 countries held the Global Civilizations Dialogue Ministerial Meeting from 10 to 11 July 2025 in Beijing,China.Focusing on the theme Safeguarding Diversity of Human Civilizations for World Peace and Development,we engaged in in-depth exchanges and reached broad consensus.
基金supported by the National Natural Science Foundation of China(NSFC)(Grant Nos.62306342,62176076)the Excellent Young Scientists Fund in Hunan Province(2024JJ4070)+3 种基金supported by the Natural Science Foundation of Guangdong(2023A1515012922)Shenzhen Foundational Research Funding(JCYJ20220818102415032)The Major Key Project of PCL(PCL2023A09)Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(2022B1212010005k).
文摘Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to explore a pre-training paradigm for CI-ToD.Nevertheless,pre-training for CI-ToD is non-trivial because it requires a large amount of multi-turn KB-grounded dialogues,which are extremely hard to collect.To alleviate the data scarcity problem for pre-training,we introduce a modularized pre-training framework(MPFToD),which is capable of utilizing large amounts of KB-free dialogues.Specifically,such modularization allows us to decouple CI-ToD into three sub-modules and propose three pre-training tasks including(i)query response matching pre-training;(ii)dialogue history consistent identification pre-training;and(iii)KB mask language modeling to enhance different abilities of CI-ToD model.As different sub-tasks are solved separately,MPFToD can learn from large amounts of KB-free dialogues for different modules,which are much easier to obtain.Results on the CI-ToD benchmark show that MPFToD pushes the state-of-the-art performance from 56.3%to 61.0%.Furthermore,we show its transferability with promising performance on other downstream tasks(i.e.,dialog act recognition,sentiment classification and table fact checking).
基金supported by the National Key Research and Development Program of China(No.2023YFF0905400)the National Natural Science Foundation of China(No.U2341229).
文摘Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low information density in dialogues,methods based on trigger enhancement have been proposed,yielding positive results.However,trigger enhancement faces challenges,which cause suboptimal model performance.First,the proportion of annotated triggers is low in DialogRE.Second,feature representations of triggers and arguments often contain conflicting information.In this paper,we propose a novel Multi-Feature Filtering and Fusion trigger enhancement approach to overcome these limitations.We first obtain representations of arguments,and triggers that contain rich semantic information through attention and gate methods.Then,we design a feature filtering mechanism that eliminates conflicting features in the encoding of trigger prototype representations and their corresponding argument pairs.Additionally,we utilize large language models to create prompts based on Chain-of-Thought and In-context Learning for automated trigger extraction.Experiments show that our model increases the average F1 score by 1.3%in the dialogue relation extraction task.Ablation and case studies confirm the effectiveness of our model.Furthermore,the feature filtering method effectively integrates with other trigger enhancement models,enhancing overall performance and demonstrating its ability to resolve feature conflicts.
基金supported by the National Natural Science Foundation of China(Grant Nos.12175106 and 92365110)the Postgraduate Research and Practice Innovation Program of Jiangsu Province,China(Grant No.KYCX23-0987).
文摘Quantum dialogue(QD)realizes the real-time secure bidirectional quantum communication.Measurement-deviceindependent(MDI)QD can resist all possible attacks focusing on the imperfect measurement devices and enhance QD’s practical security.However,in practical applications,any secure communication requires identity authentication as a prerequisite.In this paper,we propose an MDI QD protocol with bidirectional identity authentication.The practical communication parties can first authenticate the identity of each other simultaneously before the message exchange.In theory,our MDI QD protocol has unconditional security and the communication parties can exchange 1.5 bits of messages in each communication round with linear optical Bell state measurement.We numerically simulate the secrecy message capacity of our MDI QD protocol.Our protocol has two advantages.First,it can effectively resist the impersonation attack and enhance MDI QD’s practical security.Second,it does not require keys to assist the message exchange and has relatively high efficiency.Our protocol has application potential in the future quantum communication field.
文摘At a time when humanity grapples with intersecting deficits in peace,development,security and governance,civilizations stand at a crossroads.As traditional Western-led solutions falter,China’s Global Civilization Initiative(GCI)emerges as a transformative framework,translating historical wisdom into actionable strategies.Recent forums like the 11th Nishan Forum on World Civilizations and the Global Civilizations Dialogue Ministerial Meeting underscore growing consensus on core principles:equality,mutual learning,inclusive dialogue,and collaborative response to global challenges.As Chinese President Xi Jinping pointed out in his congratulatory letter to the Global Civilizations Dialogue Ministerial Meeting,“History shows that exchanges and mutual learning among civilizations are essential for civilizations to flourish and for human progress to be made.”
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12175106 and 92365110).
文摘Quantum dialogue(QD)enables two communication parties to directly exchange secret messages simultaneously.In conventional QD protocols,photons need to transmit in the quantum channel for two rounds.In this paper,we propose a one-step QD protocol based on the hyperentanglement.With the help of the non-local hyperentanglement-assisted Bell state measurement(BSM),the photons only need to transmit in the quantum channel once.We prove that our one-step QD protocol is secure in theory and numerically simulate its secret message capacity under practical experimental condition.Compared with previous QD protocols,the one-step QD protocol can effectively simplify the experiment operations and reduce the message loss caused by the photon transmission loss.Meanwhile,the non-local hyperentanglement-assisted BSM has a success probability of 100%and is feasible with linear optical elements.Moreover,combined with the hyperentanglement heralded amplification and purification,our protocol is possible to realize long-distance one-step QD.
文摘The"Decoding Zhonghua"International Conference on Dialogue among Civilisations,hosted by China International Public Relations Association,China Ethnic News and Academy of Contemporary China and World Studies was held in Beijing on January 17th.With the theme"Pursing Harmonious Coexistence of Civilisations through Dialogue".
