Due to the significance and value in human-computer interaction and natural language processing,task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.In this p...Due to the significance and value in human-computer interaction and natural language processing,task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.In this paper,we survey recent advances and challenges in task-oriented dialog systems.We also discuss three critical topics for task-oriented dialog systems:(1)improving data efficiency to facilitate dialog modeling in low-resource settings,(2)modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance,and(3)integrating domain ontology knowledge into the dialog model.Besides,we review the recent progresses in dialog evaluation and some widely-used corpora.We believe that this survey,though incomplete,can shed a light on future research in task-oriented dialog systems.展开更多
In generative dialog systems, learning representations for the dialog context is a crucial step in generating high quality responses. The dialog systems are required to capture useful and compact information from mutu...In generative dialog systems, learning representations for the dialog context is a crucial step in generating high quality responses. The dialog systems are required to capture useful and compact information from mutually dependent sentences such that the generation process can effectively attend to the central semantics. Unfortunately, existing methods may not effectively identify importance distributions for each lower position when computing an upper level feature, which may lead to the loss of information critical to the constitution of the final context representations. To address this issue, we propose a transfer learning based method named transfer hierarchical attention network(THAN). The THAN model can leverage useful prior knowledge from two related auxiliary tasks, i.e.,keyword extraction and sentence entailment, to facilitate the dialog representation learning for the main dialog generation task. During the transfer process, the syntactic structure and semantic relationship from the auxiliary tasks are distilled to enhance both the wordlevel and sentence-level attention mechanisms for the dialog system. Empirically, extensive experiments on the Twitter Dialog Corpus and the PERSONA-CHAT dataset demonstrate the effectiveness of the proposed THAN model compared with the state-of-the-art methods.展开更多
This work is about the progress of previous related work based on an experiment to improve the intelligence of robotic systems,with the aim of achieving more linguistic communication capabilities between humans and ro...This work is about the progress of previous related work based on an experiment to improve the intelligence of robotic systems,with the aim of achieving more linguistic communication capabilities between humans and robots.In this paper,the authors attempt an algorithmic approach to natural language generation through hole semantics and by applying the OMAS-III computational model as a grammatical formalism.In the original work,a technical language is used,while in the later works,this has been replaced by a limited Greek natural language dictionary.This particular effort was made to give the evolving system the ability to ask questions,as well as the authors developed an initial dialogue system using these techniques.The results show that the use of these techniques the authors apply can give us a more sophisticated dialogue system in the future.展开更多
Correction to:Transfer Hierarchical Attention Network for Generative Dialog System DOI:10.1007/s11633-019-1200-0 Authors:Xiang Zhang,Qiang Yang The article Transfer Hierarchical Attention Network for Generative Dialog...Correction to:Transfer Hierarchical Attention Network for Generative Dialog System DOI:10.1007/s11633-019-1200-0 Authors:Xiang Zhang,Qiang Yang The article Transfer Hierarchical Attention Network for Generative Dialog System written by Xiang Zhang and Qiang Yang,was originally published on vol.16,no.展开更多
The existing dataset for visual dialog comprises multiple rounds of questions and a diverse range of image contents.However,it faces challenges in overcoming visual semantic limitations,particularly in obtaining suffi...The existing dataset for visual dialog comprises multiple rounds of questions and a diverse range of image contents.However,it faces challenges in overcoming visual semantic limitations,particularly in obtaining sufficient context from visual and textual aspects of images.This paper proposes a new visual dialog dataset called Diverse History-Dialog(DS-Dialog)to address the visual semantic limitations faced by the existing dataset.DS-Dialog groups relevant histories based on their respective Microsoft Common Objects in Context(MSCOCO)image categories and consolidates them for each image.Specifically,each MSCOCO image category consists of top relevant histories extracted based on their semantic relationships between the original image caption and historical context.These relevant histories are consolidated for each image,and DS-Dialog enhances the current dataset by adding new context-aware relevant history to provide more visual semantic context for each image.The new dataset is generated through several stages,including image semantic feature extraction,keyphrase extraction,relevant question extraction,and relevant history dialog generation.The DS-Dialog dataset contains about 2.6 million question-answer pairs,where 1.3 million pairs correspond to existing VisDial’s question-answer pairs,and the remaining 1.3 million pairs include a maximum of 5 image features for each VisDial image,with each image comprising 10-round relevant question-answer pairs.Moreover,a novel adaptive relevant history selection is proposed to resolve missing visual semantic information for each image.DS-Dialog is used to benchmark the performance of previous visual dialog models and achieves better performance than previous models.Specifically,the proposed DSDialog model achieves an 8% higher mean reciprocal rank(MRR),11% higher R@1%,6% higher R@5%,5% higher R@10%,and 8% higher normalized discounted cumulative gain(NDCG)compared to LF.DS-Dialog also achieves approximately 1 point improvement on R@k,mean,MRR,and NDCG compared to the original RVA,and 2 points improvement compared to LF andDualVD.These results demonstrates the importance of the relevant semantic historical context in enhancing the visual semantic relationship between textual and visual representations of the images and questions.展开更多
On August 24,Ren Hongbin,Chairman of the China Council for the Promotion of International Trade(CCPIT),presided over the Dialog with Foreign Business Associations and Foreign-invested Enterprises and listened carefull...On August 24,Ren Hongbin,Chairman of the China Council for the Promotion of International Trade(CCPIT),presided over the Dialog with Foreign Business Associations and Foreign-invested Enterprises and listened carefully to the business operations,problems and demands,as well as opinions and suggestions of foreign business associations and foreign-invested enterprises.The participants included 11 representatives from foreign business associations,such as the American Chamber of Commerce in the People’s Republic of China(AmCham China),the European Union Chamber of Commerce in China(EUCCC),the British Chamber of Commerce in China(BCCC),and the China-Italy Chamber of Commerce(CICC),and 16 representatives of foreign-invested enterprises,such as Bayer,Boehringer Ingelheim,Nestle,Starbucks,Cargill,Corning,Intel,Qualcomm,Pfizer,Air Liquide,P&G,MUFG,and SK China.Vice Chairman Zhang Shenfeng of the CCPIT also attended the Dialog.展开更多
Over the past two decades,dialogic accounting research has evolved into a distinct field,expanding into what is now recognized as critical dialogic accounting and accountability(CDAA).The integration of critical dialo...Over the past two decades,dialogic accounting research has evolved into a distinct field,expanding into what is now recognized as critical dialogic accounting and accountability(CDAA).The integration of critical dialogic accounting and accountability acknowledges the growing need to recognize diverse pathways within accounting practices,emphasizing the representation of marginalized perspectives,engagement with power dynamics,and the analysis of conflicts,particularly in the context of societal and environmental impacts.Based on these assumptions,the Integrated Popular Reporting(IPR)is intended as a useful practical dialogic tool designed to impartially represent the viewpoints of different stakeholders.The focus extends beyond traditional dialogic accounting,integrating a newer critical lens that explores the implications of digital technology in the reporting process.To explore these advancements,the study investigates the implementation of the City of Bari’s 2020 Integrated Popular Reporting.Leveraging tools such as Talkwalker and employing a longitudinal,interventionist approach along with semi-structured interviews,the study assesses the effects of digital technologies on the dialogic accounting process.The analysis shows that the use of digital technologies has facilitated a more participatory reporting structure,evident in increased citizen engagement and reduced bureaucratic hurdles.Notably,it has enhanced the accuracy of defining citizens’informational needs and addressed pertinent themes ranging from mobility,economy,digitization,regeneration,and employment.Moreover,it underscores the need to address the digital divide and ensure inclusivity across diverse demographics.Ultimately,it contributes to the ongoing discourse on the role of technology in shaping the future of dialogic accounting and its broader implications for societal accountability.展开更多
The engagement of students is a recognised challenge for teachers.Technology offers some practical student engagement tools,and this paper examines the use of low-stakes online tests and immediate dialogic feedback to...The engagement of students is a recognised challenge for teachers.Technology offers some practical student engagement tools,and this paper examines the use of low-stakes online tests and immediate dialogic feedback to improve behavioural engagement.The academic exploration of low-stakes tests and dialogic feedback has been extensive,and they are credible teaching tools.In this study,we explore the learning benefit of their combination.Postgraduate engineering students’self-reported and learning analytics data shows conclusive evidence of improved behavioural engagement.We measured a 500%increase in the Learning Management System(LMS)page views on the days when we ran the low-stakes tests(each worth 2%of the marks for the subject)and engaged in immediate dialogic feedback.To interpret these results,we draw on theories of behavioural engagement,low-stakes tests,and feedback.We conclude that the combination of low-stakes tests and immediate feedback improves student behavioural engagement.展开更多
基金the National Natural Science Foundation of China(Grant Nos.61936010 and 61876096)the National Key R&D Program of China(Grant No.2018YFC0830200)。
文摘Due to the significance and value in human-computer interaction and natural language processing,task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.In this paper,we survey recent advances and challenges in task-oriented dialog systems.We also discuss three critical topics for task-oriented dialog systems:(1)improving data efficiency to facilitate dialog modeling in low-resource settings,(2)modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance,and(3)integrating domain ontology knowledge into the dialog model.Besides,we review the recent progresses in dialog evaluation and some widely-used corpora.We believe that this survey,though incomplete,can shed a light on future research in task-oriented dialog systems.
文摘In generative dialog systems, learning representations for the dialog context is a crucial step in generating high quality responses. The dialog systems are required to capture useful and compact information from mutually dependent sentences such that the generation process can effectively attend to the central semantics. Unfortunately, existing methods may not effectively identify importance distributions for each lower position when computing an upper level feature, which may lead to the loss of information critical to the constitution of the final context representations. To address this issue, we propose a transfer learning based method named transfer hierarchical attention network(THAN). The THAN model can leverage useful prior knowledge from two related auxiliary tasks, i.e.,keyword extraction and sentence entailment, to facilitate the dialog representation learning for the main dialog generation task. During the transfer process, the syntactic structure and semantic relationship from the auxiliary tasks are distilled to enhance both the wordlevel and sentence-level attention mechanisms for the dialog system. Empirically, extensive experiments on the Twitter Dialog Corpus and the PERSONA-CHAT dataset demonstrate the effectiveness of the proposed THAN model compared with the state-of-the-art methods.
文摘This work is about the progress of previous related work based on an experiment to improve the intelligence of robotic systems,with the aim of achieving more linguistic communication capabilities between humans and robots.In this paper,the authors attempt an algorithmic approach to natural language generation through hole semantics and by applying the OMAS-III computational model as a grammatical formalism.In the original work,a technical language is used,while in the later works,this has been replaced by a limited Greek natural language dictionary.This particular effort was made to give the evolving system the ability to ask questions,as well as the authors developed an initial dialogue system using these techniques.The results show that the use of these techniques the authors apply can give us a more sophisticated dialogue system in the future.
文摘Correction to:Transfer Hierarchical Attention Network for Generative Dialog System DOI:10.1007/s11633-019-1200-0 Authors:Xiang Zhang,Qiang Yang The article Transfer Hierarchical Attention Network for Generative Dialog System written by Xiang Zhang and Qiang Yang,was originally published on vol.16,no.
文摘The existing dataset for visual dialog comprises multiple rounds of questions and a diverse range of image contents.However,it faces challenges in overcoming visual semantic limitations,particularly in obtaining sufficient context from visual and textual aspects of images.This paper proposes a new visual dialog dataset called Diverse History-Dialog(DS-Dialog)to address the visual semantic limitations faced by the existing dataset.DS-Dialog groups relevant histories based on their respective Microsoft Common Objects in Context(MSCOCO)image categories and consolidates them for each image.Specifically,each MSCOCO image category consists of top relevant histories extracted based on their semantic relationships between the original image caption and historical context.These relevant histories are consolidated for each image,and DS-Dialog enhances the current dataset by adding new context-aware relevant history to provide more visual semantic context for each image.The new dataset is generated through several stages,including image semantic feature extraction,keyphrase extraction,relevant question extraction,and relevant history dialog generation.The DS-Dialog dataset contains about 2.6 million question-answer pairs,where 1.3 million pairs correspond to existing VisDial’s question-answer pairs,and the remaining 1.3 million pairs include a maximum of 5 image features for each VisDial image,with each image comprising 10-round relevant question-answer pairs.Moreover,a novel adaptive relevant history selection is proposed to resolve missing visual semantic information for each image.DS-Dialog is used to benchmark the performance of previous visual dialog models and achieves better performance than previous models.Specifically,the proposed DSDialog model achieves an 8% higher mean reciprocal rank(MRR),11% higher R@1%,6% higher R@5%,5% higher R@10%,and 8% higher normalized discounted cumulative gain(NDCG)compared to LF.DS-Dialog also achieves approximately 1 point improvement on R@k,mean,MRR,and NDCG compared to the original RVA,and 2 points improvement compared to LF andDualVD.These results demonstrates the importance of the relevant semantic historical context in enhancing the visual semantic relationship between textual and visual representations of the images and questions.
文摘On August 24,Ren Hongbin,Chairman of the China Council for the Promotion of International Trade(CCPIT),presided over the Dialog with Foreign Business Associations and Foreign-invested Enterprises and listened carefully to the business operations,problems and demands,as well as opinions and suggestions of foreign business associations and foreign-invested enterprises.The participants included 11 representatives from foreign business associations,such as the American Chamber of Commerce in the People’s Republic of China(AmCham China),the European Union Chamber of Commerce in China(EUCCC),the British Chamber of Commerce in China(BCCC),and the China-Italy Chamber of Commerce(CICC),and 16 representatives of foreign-invested enterprises,such as Bayer,Boehringer Ingelheim,Nestle,Starbucks,Cargill,Corning,Intel,Qualcomm,Pfizer,Air Liquide,P&G,MUFG,and SK China.Vice Chairman Zhang Shenfeng of the CCPIT also attended the Dialog.
文摘Over the past two decades,dialogic accounting research has evolved into a distinct field,expanding into what is now recognized as critical dialogic accounting and accountability(CDAA).The integration of critical dialogic accounting and accountability acknowledges the growing need to recognize diverse pathways within accounting practices,emphasizing the representation of marginalized perspectives,engagement with power dynamics,and the analysis of conflicts,particularly in the context of societal and environmental impacts.Based on these assumptions,the Integrated Popular Reporting(IPR)is intended as a useful practical dialogic tool designed to impartially represent the viewpoints of different stakeholders.The focus extends beyond traditional dialogic accounting,integrating a newer critical lens that explores the implications of digital technology in the reporting process.To explore these advancements,the study investigates the implementation of the City of Bari’s 2020 Integrated Popular Reporting.Leveraging tools such as Talkwalker and employing a longitudinal,interventionist approach along with semi-structured interviews,the study assesses the effects of digital technologies on the dialogic accounting process.The analysis shows that the use of digital technologies has facilitated a more participatory reporting structure,evident in increased citizen engagement and reduced bureaucratic hurdles.Notably,it has enhanced the accuracy of defining citizens’informational needs and addressed pertinent themes ranging from mobility,economy,digitization,regeneration,and employment.Moreover,it underscores the need to address the digital divide and ensure inclusivity across diverse demographics.Ultimately,it contributes to the ongoing discourse on the role of technology in shaping the future of dialogic accounting and its broader implications for societal accountability.
文摘The engagement of students is a recognised challenge for teachers.Technology offers some practical student engagement tools,and this paper examines the use of low-stakes online tests and immediate dialogic feedback to improve behavioural engagement.The academic exploration of low-stakes tests and dialogic feedback has been extensive,and they are credible teaching tools.In this study,we explore the learning benefit of their combination.Postgraduate engineering students’self-reported and learning analytics data shows conclusive evidence of improved behavioural engagement.We measured a 500%increase in the Learning Management System(LMS)page views on the days when we ran the low-stakes tests(each worth 2%of the marks for the subject)and engaged in immediate dialogic feedback.To interpret these results,we draw on theories of behavioural engagement,low-stakes tests,and feedback.We conclude that the combination of low-stakes tests and immediate feedback improves student behavioural engagement.
