The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing. To improve state tracking quality, we argue that relationships between different aspects of dialogue state must be taken into account as they can often guide a more accurate interpretation process. To this end, we present an energy-based approach to dialogue state tracking as a structured classification task. The novelty of our approach lies in the use of an energy network on top of a deep learning architecture to explore more signal correlations between network variables including input features and output labels. We demonstrate that the energy-based approach improves the performance of a deep learning dialogue state tracker towards state-of-the-art results without the need for many of the other steps required by current state-of-the-art methods.
{"title":"Energy-Based Modelling for Dialogue State Tracking","authors":"A. Trinh, R. Ross, John D. Kelleher","doi":"10.18653/v1/W19-4109","DOIUrl":"https://doi.org/10.18653/v1/W19-4109","url":null,"abstract":"The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing. To improve state tracking quality, we argue that relationships between different aspects of dialogue state must be taken into account as they can often guide a more accurate interpretation process. To this end, we present an energy-based approach to dialogue state tracking as a structured classification task. The novelty of our approach lies in the use of an energy network on top of a deep learning architecture to explore more signal correlations between network variables including input features and output labels. We demonstrate that the energy-based approach improves the performance of a deep learning dialogue state tracker towards state-of-the-art results without the need for many of the other steps required by current state-of-the-art methods.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133748356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A sequence-to-sequence model tends to generate generic responses with little information for input utterances. To solve this problem, we propose a neural model that generates relevant and informative responses. Our model has simple architecture to enable easy application to existing neural dialogue models. Specifically, using positive pointwise mutual information, it first identifies keywords that frequently co-occur in responses given an utterance. Then, the model encourages the decoder to use the keywords for response generation. Experiment results demonstrate that our model successfully diversifies responses relative to previous models.
{"title":"Relevant and Informative Response Generation using Pointwise Mutual Information","authors":"Junya Takayama, Yuki Arase","doi":"10.18653/v1/W19-4115","DOIUrl":"https://doi.org/10.18653/v1/W19-4115","url":null,"abstract":"A sequence-to-sequence model tends to generate generic responses with little information for input utterances. To solve this problem, we propose a neural model that generates relevant and informative responses. Our model has simple architecture to enable easy application to existing neural dialogue models. Specifically, using positive pointwise mutual information, it first identifies keywords that frequently co-occur in responses given an utterance. Then, the model encourages the decoder to use the keywords for response generation. Experiment results demonstrate that our model successfully diversifies responses relative to previous models.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131809489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dialogue systems and conversational agents are becoming increasingly popular in modern society. We conceptualized one such conversational agent, Microsoft’s “Ruuh” with the promise to be able to talk to its users on any subject they choose. Building an open-ended conversational agent like Ruuh at onset seems like a daunting task, since the agent needs to think beyond the utilitarian notion of merely generating “relevant” responses and meet a wider range of user social needs, like expressing happiness when user’s favourite sports team wins, sharing a cute comment on showing the pictures of the user’s pet and so on. The agent also needs to detect and respond to abusive language, sensitive topics and trolling behaviour of the users. Many of these problems pose significant research challenges as well as product design limitations as one needs to circumnavigate the technical limitations to create an acceptable user experience. However, as the product reaches the real users the true test begins, and one realizes the challenges and opportunities that lie in the vast domain of conversations. With over 2.5 million real-world users till date who have generated over 300 million user conversations with Ruuh, there is a plethora of learning, insights and opportunities that we will talk about in this paper.
{"title":"Insights from Building an Open-Ended Conversational Agent","authors":"Khyatti Gupta, Meghana Joshi, Ankush Chatterjee, Sonam Damani, Kedhar Nath Narahari, Puneet Agrawal","doi":"10.18653/v1/W19-4112","DOIUrl":"https://doi.org/10.18653/v1/W19-4112","url":null,"abstract":"Dialogue systems and conversational agents are becoming increasingly popular in modern society. We conceptualized one such conversational agent, Microsoft’s “Ruuh” with the promise to be able to talk to its users on any subject they choose. Building an open-ended conversational agent like Ruuh at onset seems like a daunting task, since the agent needs to think beyond the utilitarian notion of merely generating “relevant” responses and meet a wider range of user social needs, like expressing happiness when user’s favourite sports team wins, sharing a cute comment on showing the pictures of the user’s pet and so on. The agent also needs to detect and respond to abusive language, sensitive topics and trolling behaviour of the users. Many of these problems pose significant research challenges as well as product design limitations as one needs to circumnavigate the technical limitations to create an acceptable user experience. However, as the product reaches the real users the true test begins, and one realizes the challenges and opportunities that lie in the vast domain of conversations. With over 2.5 million real-world users till date who have generated over 300 million user conversations with Ruuh, there is a plethora of learning, insights and opportunities that we will talk about in this paper.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126665734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A neural conversation model is a promising approach to develop dialogue systems with the ability of chit-chat. It allows training a model in an end-to-end manner without complex rule design nor feature engineering. However, as a side effect, the neural model tends to generate safe but uninformative and insensitive responses like “OK” and “I don’t know.” Such replies are called generic responses and regarded as a critical problem for user-engagement of dialogue systems. For a more engaging chit-chat experience, we propose a neural conversation model that generates responsive and self-expressive replies. Specifically, our model generates domain-aware and sentiment-rich responses. Experiments empirically confirmed that our model outperformed the sequence-to-sequence model; 68.1% of our responses were domain-aware with sentiment polarities, which was only 2.7% for responses generated by the sequence-to-sequence model.
{"title":"Responsive and Self-Expressive Dialogue Generation","authors":"Kozo Chikai, Junya Takayama, Yuki Arase","doi":"10.18653/v1/W19-4116","DOIUrl":"https://doi.org/10.18653/v1/W19-4116","url":null,"abstract":"A neural conversation model is a promising approach to develop dialogue systems with the ability of chit-chat. It allows training a model in an end-to-end manner without complex rule design nor feature engineering. However, as a side effect, the neural model tends to generate safe but uninformative and insensitive responses like “OK” and “I don’t know.” Such replies are called generic responses and regarded as a critical problem for user-engagement of dialogue systems. For a more engaging chit-chat experience, we propose a neural conversation model that generates responsive and self-expressive replies. Specifically, our model generates domain-aware and sentiment-rich responses. Experiments empirically confirmed that our model outperformed the sequence-to-sequence model; 68.1% of our responses were domain-aware with sentiment polarities, which was only 2.7% for responses generated by the sequence-to-sequence model.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131721103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chulaka Gunasekara, Jonathan K. Kummerfeld, L. Polymenakos, Walter S. Lasecki
Goal-oriented dialogue in complex domains is an extremely challenging problem and there are relatively few datasets. This task provided two new resources that presented different challenges: one was focused but small, while the other was large but diverse. We also considered several new variations on the next utterance selection problem: (1) increasing the number of candidates, (2) including paraphrases, and (3) not including a correct option in the candidate set. Twenty teams participated, developing a range of neural network models, including some that successfully incorporated external data to boost performance. Both datasets have been publicly released, enabling future work to build on these results, working towards robust goal-oriented dialogue systems.
{"title":"DSTC7 Task 1: Noetic End-to-End Response Selection","authors":"Chulaka Gunasekara, Jonathan K. Kummerfeld, L. Polymenakos, Walter S. Lasecki","doi":"10.18653/v1/W19-4107","DOIUrl":"https://doi.org/10.18653/v1/W19-4107","url":null,"abstract":"Goal-oriented dialogue in complex domains is an extremely challenging problem and there are relatively few datasets. This task provided two new resources that presented different challenges: one was focused but small, while the other was large but diverse. We also considered several new variations on the next utterance selection problem: (1) increasing the number of candidates, (2) including paraphrases, and (3) not including a correct option in the candidate set. Twenty teams participated, developing a range of neural network models, including some that successfully incorporated external data to boost performance. Both datasets have been publicly released, enabling future work to build on these results, working towards robust goal-oriented dialogue systems.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114799227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Yang, Rui Qiao, Haocheng Qin, Amy Sun, Luchen Tan, Kun Xiong, Ming Li
We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context. Following a standard decomposition of the context reconstruction task into referring expression detection and coreference resolution, we propose a novel end-to-end architecture for separately and jointly accomplishing this task. Key features of this model include POS and position encoding using CNNs and a novel pronoun masking mechanism. One perennial problem in building such models is the paucity of training data, which we address by augmenting previously-proposed methods to generate a large amount of realistic training data. The combination of more data and better models yields accuracy higher than the state-of-the-art method in coreference resolution and end-to-end context reconstruction.
{"title":"End-to-End Neural Context Reconstruction in Chinese Dialogue","authors":"Wei Yang, Rui Qiao, Haocheng Qin, Amy Sun, Luchen Tan, Kun Xiong, Ming Li","doi":"10.18653/v1/W19-4108","DOIUrl":"https://doi.org/10.18653/v1/W19-4108","url":null,"abstract":"We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context. Following a standard decomposition of the context reconstruction task into referring expression detection and coreference resolution, we propose a novel end-to-end architecture for separately and jointly accomplishing this task. Key features of this model include POS and position encoding using CNNs and a novel pronoun masking mechanism. One perennial problem in building such models is the paucity of training data, which we address by augmenting previously-proposed methods to generate a large amount of realistic training data. The combination of more data and better models yields accuracy higher than the state-of-the-art method in coreference resolution and end-to-end context reconstruction.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125898021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This theoretical paper identifies a need for a definition of asymmetric co-creativity where creativity is expected from the computational agent but not from the human user. Our co-operative creativity framework takes into account that the computational agent has a message to convey in a co-operative fashion, which introduces a trade-off on how creative the computer can be. The requirements of co-operation are identified from an interdisciplinary point of view. We divide co-operative creativity in message creativity, contextual creativity and communicative creativity. Finally these notions are applied in the context of the Peace Machine system concept.
{"title":"Co-Operation as an Asymmetric Form of Human-Computer Creativity. Case: Peace Machine","authors":"Mika Hämäläinen, T. Honkela","doi":"10.18653/v1/W19-4105","DOIUrl":"https://doi.org/10.18653/v1/W19-4105","url":null,"abstract":"This theoretical paper identifies a need for a definition of asymmetric co-creativity where creativity is expected from the computational agent but not from the human user. Our co-operative creativity framework takes into account that the computational agent has a message to convey in a co-operative fashion, which introduces a trade-off on how creative the computer can be. The requirements of co-operation are identified from an interdisciplinary point of view. We divide co-operative creativity in message creativity, contextual creativity and communicative creativity. Finally these notions are applied in the context of the Peace Machine system concept.","PeriodicalId":178445,"journal":{"name":"Proceedings of the First Workshop on NLP for Conversational AI","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131843115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：