Distinguished vips,Ladies and gentlemen,friends,With the joint efforts of all of you,the 2013"Understanding&Cooperation"Dialogue,held by the Chinese Association for International Understanding(CAFIU)ha...Distinguished vips,Ladies and gentlemen,friends,With the joint efforts of all of you,the 2013"Understanding&Cooperation"Dialogue,held by the Chinese Association for International Understanding(CAFIU)has successfully completed all items on its agenda.It’s time to bid farewell.During the past 4 days,we came across over half China from Beijing to Jiangxi Province,feeling the hot summer days and witnessing展开更多
Distinguished vips,Ladies and Gentlemen,Dear friends,On behalf of the Chinese Association for International Understanding(CAFIU),I would like to start by extending my warmest welcome to all representatives from home...Distinguished vips,Ladies and Gentlemen,Dear friends,On behalf of the Chinese Association for International Understanding(CAFIU),I would like to start by extending my warmest welcome to all representatives from home and abroad,who come to attend the 2013"Understanding展开更多
Distinguished vips,Ladies and gentlemen,Dear friends,It gives me great pleasure to meet all of you in Beijing and join you in the 2013"Understanding and Cooperation"Dialogue.Please allow me to begin by ext...Distinguished vips,Ladies and gentlemen,Dear friends,It gives me great pleasure to meet all of you in Beijing and join you in the 2013"Understanding and Cooperation"Dialogue.Please allow me to begin by extending my warmest congratulations to the opening of this Dialogue,and my展开更多
正Distinguished vips, ladies and gentlemen, dear friends: Today we meet here in picturesque Hangzhou for the 2012 Understanding and Cooperation Dialogue Part II: New-type Community and Harmonious Society. On behalf ...正Distinguished vips, ladies and gentlemen, dear friends: Today we meet here in picturesque Hangzhou for the 2012 Understanding and Cooperation Dialogue Part II: New-type Community and Harmonious Society. On behalf of the National Committee展开更多
正The 2012 Understanding and Cooperation Dialogue opens today. I'd like to extend heartfelt congratulations to the convening of the Dialogue, as well as my warm welcome to the political leaders and friends from di...正The 2012 Understanding and Cooperation Dialogue opens today. I'd like to extend heartfelt congratulations to the convening of the Dialogue, as well as my warm welcome to the political leaders and friends from different countries who have come to China for the Dialogue.展开更多
正Today we convene a great international forum under the strong leadership of the Chinese side. I would like to express my sincere gratitude to the sponsors for granting me an opportunity to speak here.
正Director of Ceremonies, Your Excellencies, Ministers here present, Chinese State Leaders, Heads of Chinese NGOs, Representatives of International NGOs, Ladies and Gentlemen, Let me first and foremost express my hear...正Director of Ceremonies, Your Excellencies, Ministers here present, Chinese State Leaders, Heads of Chinese NGOs, Representatives of International NGOs, Ladies and Gentlemen, Let me first and foremost express my heartfelt gratitude to the Chinese Association for International Understanding for inviting me to展开更多
正The Understanding and Cooperation Dialogue, Sponsored by the Chinese Association for International Understanding (CAFIU) and the China Foundation for Peace and Development (CFPD), and Co-organized by the Chinese Peo...正The Understanding and Cooperation Dialogue, Sponsored by the Chinese Association for International Understanding (CAFIU) and the China Foundation for Peace and Development (CFPD), and Co-organized by the Chinese People' s Association for Peace and展开更多
正Let me begin with extending my warmest welcome to domestic and overseas vips. Centered on the topics, the delegates have conducted frank exchanges and in-depth discussions, which helped to enhance understanding an...正Let me begin with extending my warmest welcome to domestic and overseas vips. Centered on the topics, the delegates have conducted frank exchanges and in-depth discussions, which helped to enhance understanding and friendship, and improve consensus and cooperation. With the joint efforts of all展开更多
正Ladies and gentlemen, dear friends, On behalf of the sponsor organization-Chinese Association for International Understanding (CAFIU), let me begin with extending my warm welcome to all distinguished vips and dele...正Ladies and gentlemen, dear friends, On behalf of the sponsor organization-Chinese Association for International Understanding (CAFIU), let me begin with extending my warm welcome to all distinguished vips and delegates from home and abroad present at the 2012 Understanding and Cooperation Dialogue, as well as my展开更多
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
Human-Computer dialogue systems provide a natural language based interface between human and computers. They are widely demanded in network information services, intelligent accompanying robots, and so on. A Human-Com...Human-Computer dialogue systems provide a natural language based interface between human and computers. They are widely demanded in network information services, intelligent accompanying robots, and so on. A Human-Computer dialogue system typically consists of three parts, namely Natural Language Understanding （NLU）, Dialogue Management （DM） and Natural Language Generation （NLG）. Each part has several different subtasks. Each subtask has been received lots of attentions, many improvements have been achieved on each subtask, respectively. But systems built in traditional pipeline way, where different subtasks are assembled sequently, suffered from some problems such as error accu- mulation and expanding, domain transferring. Therefore, researches on jointly modeling several subtasks in one part or cross different parts have been prompted greatly in recent years, especially the rapid developments on deep neural networks based joint models. There is even a few work aiming to integrate all subtasks of a dialogue system in a single model, namely end-to-end models. This paper introduces two basic frames of current dialogue systems and gives a brief survey on recent advances on variety subtasks at first, and then focuses on joint models for multiple subtasks of dialogues. We review several different joint models including integration of several subtasks inside NLU or NLG, jointly modeling cross NLG and DM, and jointly modeling through NLU, DM and NLG. Both advantages and problems of those joint models are discussed. We consider that the joint models, or end-to-end models, will be one important trend for developing Human-Computer dialogue systems.展开更多
SHTQS is an intelligent telephone-besed spoken dialyze system providing the infomation about the best route between two sites in Shanghai. Instead of separated parts of speech decoding and language parsing, a close co...SHTQS is an intelligent telephone-besed spoken dialyze system providing the infomation about the best route between two sites in Shanghai. Instead of separated parts of speech decoding and language parsing, a close cool,ration is carded out in SHTQS by integrating automatic speech recognizer （AS,R）, language understanding, dialogue management and speech generatot. In such a way, the erroneous analysis and uncertainty happening in the preceding stages would be recovered and determined acourately with high-level knowledge, Moreover, instead of shallow word-level analysis or simply keyword or key phrase matching, a deeper analysis is performed in our system by integrating a robust parser and a semantic interpreter. The robust parser is particularly important for spontanecos speech inputs because most of the inquiry sentences/phrases are ill-formed. In addition, in designinga mixed-initiative dialogue system, understanding users＇ inquiries is essential; however, simply matching keywords and/or key phrases can hardly achieve this. Therefore, a semantic interpreter is incorporated in oar system. The performnce of is also evaluated. The dialogue efficiency is 4.4 sentences per query on an average and the case precision rate of language understanding module is up to 81%. The results are satisfactory.展开更多
Spoken dialogue systems are an active research field with wide applications. But the differences in the Chinese spoken dialogue system are not as distinct as that of English. In Chinese spoken dialogues, there are man...Spoken dialogue systems are an active research field with wide applications. But the differences in the Chinese spoken dialogue system are not as distinct as that of English. In Chinese spoken dialogues, there are many language phenomena. Firstly, most utterances are ill-formed. Secondly, ellipsis, anaphora and negation are also widely used in Chinese spoken dialogue. Determining how to extract semantic information from incomplete sentences and resolve negation, anaphora and ellipsis is crucial. SHTQS (Shanghai Transportation Query System) is an intelligent telephone-based spoken dialogue system providing information about the best route between any two sites in Shanghai. After a brief description of the system, the natural language processing is emphasized. Speech recognition sentences unavoidably contain errors. In language sequence processing procedures, these errors can be easily passed to the later parts and take on a ripple effect. To detect and recover these from errors as early as possible, language-processing strategies are specially considered. For errors resulting from divided words in speech recognition, segmentation and POS Tagging approaches that can rectify these errors are designed. Since most of the inquiry utterances are ill-formed and negation, anaphora and ellipsis are common language phenomena, the language understanding must be adequately adaptive. So, a partial syntactic parsing scheme is adopted and a chart algorithm is used. The parser is based on unification grammar. The semantic frame that extracts from the best arc set of the chart is used to represent the meaning of sentences. The negation, anaphora and ellipsis are also analyzed and corresponding processing approaches are presented. The accuracy of the language processing part is 88.39% and the testing result shows that the language processing strategies are rational and effective.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
Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue pol...Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue policy.Reinforcement learning(RL)is widely used to optimize this dialogue policy.In the learning process,the user is regarded as the environment and the system as the agent.In this paper,we present an overview of the recent advances and challenges in dialogue policy from the perspective of RL.More specifically,we identify the problems and summarize corresponding solutions for RL-based dialogue policy learning.In addition,we provide a comprehensive survey of applying RL to DPL by categorizing recent methods into five basic elements in RL.We believe this survey can shed light on future research in DPL.展开更多
This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manu...This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus.However,the annotation of the corpus is costly,time-consuming,and cannot cover a wide range of domains in the real world.To solve this problem,we propose a multi-span prediction network(MSPN)that performs unsupervised DST for end-to-end task-oriented dialogue.Specifically,MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords.Based on these keywords,MSPN uses a semantic distance based clustering approach to obtain the values of each slot.In addition,we propose an ontology-based reinforcement learning approach,which employs the values of each slot to train MSPN to generate relevant values.Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements.Besides,we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain,which further demonstrates the adaptability of MSPN.展开更多
One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or restaurants.Recently,the encoder-decoder mod...One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or restaurants.Recently,the encoder-decoder model based on the end-to-end neural network has become an attractive approach to meet this challenge.However,it usually requires a sufficiently large amount of training data and it is not flexible to handle dialogue state transition.This paper addresses these problems by proposing a simple but practical framework called Multi-Domain KB-BOT(MDKB-BOT),which leverages both neural networks and rule-based strategy in natural language understanding(NLU)and dialogue management(DM).Experiments on the data set of the Chinese Human-Computer Dialogue Technology Evaluation Campaign show that MDKB-BOT achieves competitive performance on several evaluation metrics,including task completion rate and user satisfaction.展开更多
文摘Distinguished vips,Ladies and gentlemen,friends,With the joint efforts of all of you,the 2013"Understanding&Cooperation"Dialogue,held by the Chinese Association for International Understanding(CAFIU)has successfully completed all items on its agenda.It’s time to bid farewell.During the past 4 days,we came across over half China from Beijing to Jiangxi Province,feeling the hot summer days and witnessing
文摘Distinguished vips,Ladies and Gentlemen,Dear friends,On behalf of the Chinese Association for International Understanding(CAFIU),I would like to start by extending my warmest welcome to all representatives from home and abroad,who come to attend the 2013"Understanding
文摘Distinguished vips,Ladies and gentlemen,Dear friends,It gives me great pleasure to meet all of you in Beijing and join you in the 2013"Understanding and Cooperation"Dialogue.Please allow me to begin by extending my warmest congratulations to the opening of this Dialogue,and my
文摘正Distinguished vips, ladies and gentlemen, dear friends: Today we meet here in picturesque Hangzhou for the 2012 Understanding and Cooperation Dialogue Part II: New-type Community and Harmonious Society. On behalf of the National Committee
文摘正The 2012 Understanding and Cooperation Dialogue opens today. I'd like to extend heartfelt congratulations to the convening of the Dialogue, as well as my warm welcome to the political leaders and friends from different countries who have come to China for the Dialogue.
文摘正Today we convene a great international forum under the strong leadership of the Chinese side. I would like to express my sincere gratitude to the sponsors for granting me an opportunity to speak here.
文摘正Director of Ceremonies, Your Excellencies, Ministers here present, Chinese State Leaders, Heads of Chinese NGOs, Representatives of International NGOs, Ladies and Gentlemen, Let me first and foremost express my heartfelt gratitude to the Chinese Association for International Understanding for inviting me to
文摘正The Understanding and Cooperation Dialogue, Sponsored by the Chinese Association for International Understanding (CAFIU) and the China Foundation for Peace and Development (CFPD), and Co-organized by the Chinese People' s Association for Peace and
文摘正Let me begin with extending my warmest welcome to domestic and overseas vips. Centered on the topics, the delegates have conducted frank exchanges and in-depth discussions, which helped to enhance understanding and friendship, and improve consensus and cooperation. With the joint efforts of all
文摘正Ladies and gentlemen, dear friends, On behalf of the sponsor organization-Chinese Association for International Understanding (CAFIU), let me begin with extending my warm welcome to all distinguished vips and delegates from home and abroad present at the 2012 Understanding and Cooperation Dialogue, as well as my
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Human-Computer dialogue systems provide a natural language based interface between human and computers. They are widely demanded in network information services, intelligent accompanying robots, and so on. A Human-Computer dialogue system typically consists of three parts, namely Natural Language Understanding （NLU）, Dialogue Management （DM） and Natural Language Generation （NLG）. Each part has several different subtasks. Each subtask has been received lots of attentions, many improvements have been achieved on each subtask, respectively. But systems built in traditional pipeline way, where different subtasks are assembled sequently, suffered from some problems such as error accu- mulation and expanding, domain transferring. Therefore, researches on jointly modeling several subtasks in one part or cross different parts have been prompted greatly in recent years, especially the rapid developments on deep neural networks based joint models. There is even a few work aiming to integrate all subtasks of a dialogue system in a single model, namely end-to-end models. This paper introduces two basic frames of current dialogue systems and gives a brief survey on recent advances on variety subtasks at first, and then focuses on joint models for multiple subtasks of dialogues. We review several different joint models including integration of several subtasks inside NLU or NLG, jointly modeling cross NLG and DM, and jointly modeling through NLU, DM and NLG. Both advantages and problems of those joint models are discussed. We consider that the joint models, or end-to-end models, will be one important trend for developing Human-Computer dialogue systems.
文摘SHTQS is an intelligent telephone-besed spoken dialyze system providing the infomation about the best route between two sites in Shanghai. Instead of separated parts of speech decoding and language parsing, a close cool,ration is carded out in SHTQS by integrating automatic speech recognizer （AS,R）, language understanding, dialogue management and speech generatot. In such a way, the erroneous analysis and uncertainty happening in the preceding stages would be recovered and determined acourately with high-level knowledge, Moreover, instead of shallow word-level analysis or simply keyword or key phrase matching, a deeper analysis is performed in our system by integrating a robust parser and a semantic interpreter. The robust parser is particularly important for spontanecos speech inputs because most of the inquiry sentences/phrases are ill-formed. In addition, in designinga mixed-initiative dialogue system, understanding users＇ inquiries is essential; however, simply matching keywords and/or key phrases can hardly achieve this. Therefore, a semantic interpreter is incorporated in oar system. The performnce of is also evaluated. The dialogue efficiency is 4.4 sentences per query on an average and the case precision rate of language understanding module is up to 81%. The results are satisfactory.
文摘Spoken dialogue systems are an active research field with wide applications. But the differences in the Chinese spoken dialogue system are not as distinct as that of English. In Chinese spoken dialogues, there are many language phenomena. Firstly, most utterances are ill-formed. Secondly, ellipsis, anaphora and negation are also widely used in Chinese spoken dialogue. Determining how to extract semantic information from incomplete sentences and resolve negation, anaphora and ellipsis is crucial. SHTQS (Shanghai Transportation Query System) is an intelligent telephone-based spoken dialogue system providing information about the best route between any two sites in Shanghai. After a brief description of the system, the natural language processing is emphasized. Speech recognition sentences unavoidably contain errors. In language sequence processing procedures, these errors can be easily passed to the later parts and take on a ripple effect. To detect and recover these from errors as early as possible, language-processing strategies are specially considered. For errors resulting from divided words in speech recognition, segmentation and POS Tagging approaches that can rectify these errors are designed. Since most of the inquiry utterances are ill-formed and negation, anaphora and ellipsis are common language phenomena, the language understanding must be adequately adaptive. So, a partial syntactic parsing scheme is adopted and a chart algorithm is used. The parser is based on unification grammar. The semantic frame that extracts from the best arc set of the chart is used to represent the meaning of sentences. The negation, anaphora and ellipsis are also analyzed and corresponding processing approaches are presented. The accuracy of the language processing part is 88.39% and the testing result shows that the language processing strategies are rational and effective.
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Innovation and Technology Fund(ITF),Government of the Hong Kong Special Administrative Region(HKSAR),China(No.PRP-054-21FX).
文摘Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue policy.Reinforcement learning(RL)is widely used to optimize this dialogue policy.In the learning process,the user is regarded as the environment and the system as the agent.In this paper,we present an overview of the recent advances and challenges in dialogue policy from the perspective of RL.More specifically,we identify the problems and summarize corresponding solutions for RL-based dialogue policy learning.In addition,we provide a comprehensive survey of applying RL to DPL by categorizing recent methods into five basic elements in RL.We believe this survey can shed light on future research in DPL.
基金supported by the National Key Research and Development Program of China under Grant No.2020AAA0106400the National Natural Science Foundation of China under Grant Nos.61922085 and 61976211+2 种基金the Independent Research Project of National Laboratory of Pattern Recognition under Grant No.Z-2018013the Key Research Program of Chinese Academy of Sciences(CAS)under Grant No.ZDBS-SSW-JSC006the Youth Innovation Promotion Association CAS under Grant No.201912.
文摘This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus.However,the annotation of the corpus is costly,time-consuming,and cannot cover a wide range of domains in the real world.To solve this problem,we propose a multi-span prediction network(MSPN)that performs unsupervised DST for end-to-end task-oriented dialogue.Specifically,MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords.Based on these keywords,MSPN uses a semantic distance based clustering approach to obtain the values of each slot.In addition,we propose an ontology-based reinforcement learning approach,which employs the values of each slot to train MSPN to generate relevant values.Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements.Besides,we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain,which further demonstrates the adaptability of MSPN.
基金This work was supported by Beijing Natural Science Foundation(No.4174098)National Natural Science Foundation of China(No.61702047)the Fundamental Research Funds for the Central Universities(No.2017RC02).
文摘One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or restaurants.Recently,the encoder-decoder model based on the end-to-end neural network has become an attractive approach to meet this challenge.However,it usually requires a sufficiently large amount of training data and it is not flexible to handle dialogue state transition.This paper addresses these problems by proposing a simple but practical framework called Multi-Domain KB-BOT(MDKB-BOT),which leverages both neural networks and rule-based strategy in natural language understanding(NLU)and dialogue management(DM).Experiments on the data set of the Chinese Human-Computer Dialogue Technology Evaluation Campaign show that MDKB-BOT achieves competitive performance on several evaluation metrics,including task completion rate and user satisfaction.
