The Experts below are selected from a list of 255 Experts worldwide ranked by ideXlab platform

Rui Yan - One of the best experts on this subject based on the ideXlab platform.

  • Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce
    arXiv: Computation and Language, 2019
    Co-Authors: Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan
    Abstract:

    Information-seeking Conversation System aims at satisfying the information needs of users through Conversations. Text matching between a user query and a pre-collected question is an important part of the information-seeking Conversation in E-commerce. In the practical scenario, a sort of questions always correspond to a same answer. Naturally, these questions can form a bag. Learning the matching between user query and bag directly may improve the Conversation performance, denoted as query-bag matching. Inspired by such opinion, we propose a query-bag matching model which mainly utilizes the mutual coverage between query and bag and measures the degree of the content in the query mentioned by the bag, and vice verse. In addition, the learned bag representation in word level helps find the main points of a bag in a fine grade and promotes the query-bag matching performance. Experiments on two datasets show the effectiveness of our model.

  • CIKM - Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce
    Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019
    Co-Authors: Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan
    Abstract:

    Information-seeking Conversation System aims at satisfying the information needs of users through Conversations. Text matching between a user query and a pre-collected question is an important part of the information-seeking Conversation in E-commerce. In the practical scenario, a sort of questions always correspond to a same answer. Naturally, these questions can form a bag. Learning the matching between user query and bag directly may improve the Conversation performance, denoted as query-bag matching. Inspired by such opinion, we propose a query-bag matching model which mainly utilizes the mutual coverage between query and bag and measures the degree of the content in the query mentioned by the bag, and vice verse. In addition, the learned bag representation in word level helps find the main points of a bag in a fine grade and promotes the query-bag matching performance. Experiments on two datasets show the effectiveness of our model.

  • IJCAI - An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
    Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
    Co-Authors: Yiping Song, Dongyan Zhao, Ming Zhang, Jian-yun Nie, Rui Yan
    Abstract:

     Human-computer Conversation Systems have attracted much attention in Natural Language Processing. Conversation Systems can be roughly divided into two categories: retrieval-based and generation-based Systems. Retrieval Systems search a user-issued utterance (namely a query ) in a large Conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based Conversation System. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble System outperforms each single module by a large margin.

  • WWW (Companion Volume) - A NeuRetrieval Model for Human-Computer Conversations
    Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018
    Co-Authors: Rui Yan, Dongyan Zhao
    Abstract:

    To establish an automatic Conversation System between human and computer is regarded as one of the most hardcore problems in computer science. It requires interdisciplinary techniques of information retrieval, natural language processing, data management as well as artificial intelligence. The arrival of big data era reveals the feasibility to create a Conversation System empowered by data-driven approaches. Now we are able to collect extremely large Conversational data on Web, and organize them to launch a human-computer Conversation System. Owing to the diversity of Web resources available, a retrieval-based Conversation System will be able to find at least some responses from the massive data repository for any user inputs. Given a human issued utterance, i.e., a query, a retrieval-based Conversation System will search for appropriate replies, conduct a relevance ranking, and then output the highly relevant one as the response. In this paper, we propose a novel retrieval model named NeuRetrieval for short text understanding, representation and semantic matching. The proposed model is general and unified for both single-turn and multi-turn Conversation scenarios in open domain. In the experiments, we investigate the effectiveness of the proposed deep neural network model for human-computer Conversations. We demonstrate performance improvement against a series of baseline methods in several evaluation metrics. In contrast with previously proposed methods, NeuRetrieval is tailored for Conversation scenarios and demonstrated to be more effective.

  • joint learning of response ranking and next utterance suggestion in human computer Conversation System
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017
    Co-Authors: Rui Yan, Dongyan Zhao, E Weinan
    Abstract:

    Conversation Systems are of growing importance since they enable an easy interaction interface between humans and computers: using natural languages. To build a Conversation System with adequate intelligence is challenging, and requires abundant resources including an acquisition of big data and interdisciplinary techniques, such as information retrieval and natural language processing. Along with the prosperity of Web 2.0, the massive data available greatly facilitate data-driven methods such as deep learning for human-computer Conversation Systems. Owing to the diversity of Web resources, a retrieval-based Conversation System will come up with at least some results from the immense repository for any user inputs. Given a human issued message, i.e., query, a traditional Conversation System would provide a response after adequate training and learning of how to respond. In this paper, we propose a new task for Conversation Systems: joint learning of response ranking featured with next utterance suggestion. We assume that the new Conversation mode is more proactive and keeps user engaging. We examine the assumption in experiments. Besides, to address the joint learning task, we propose a novel Dual-LSTM Chain Model to couple response ranking and next utterance suggestion simultaneously. From the experimental results, we demonstrate the usefulness of the proposed task and the effectiveness of the proposed model.

Naoyuki Kubota - One of the best experts on this subject based on the ideXlab platform.

  • A Socially Interactive Robot Partner Using Content-Based Conversation System for Information Support
    Journal of Advanced Computational Intelligence and Intelligent Informatics, 2018
    Co-Authors: Jinseok Woo, Janos Botzheim, Naoyuki Kubota
    Abstract:

    The development of robot partners for supporting human life has been growing for many years. One main feature that should be considered in developing such robots is the Conversation System. In this study, a Conversation System called iPhonoid-C is introduced. The iPhonoid-C is a robot partner based on a smart device. A Conversation is a form of communication in which two or more people exchange words and information. Therefore, one important part of judging the effectiveness of the interaction must be to evaluate if the appropriate amount of information is provided by the robot. In this research, we focused on a time-dependent utterance System to adjust the amount of Conversation based on Grice’s maxim of quantity. By utilizing Grice’s theory, it is possible to tailor the robot’s communication by selecting the Grice value to correspond to the human’s condition. Using this method, the robot partner can control the amount of information it communicates to adapt to the human’s situation based on Grice’s maxim of quantity. An experimental result with the robot partner is presented to validate the proposed time-dependent Conversation System.

  • Conversation System based on computational intelligence for robot partner using smart phone
    Systems Man and Cybernetics, 2013
    Co-Authors: Jinseok Woo, Naoyuki Kubota
    Abstract:

    This paper proposes a Conversation System based on multimodal perception for verbal communication between a human and a robot partner using various types of sensors. First, we describe the control structure of the robot partner and explain the architecture of the robot System. Next, evolutionary robot vision is applied to human and object detection. Next, a Conversation System based on information ally structured space is proposed. Furthermore, we propose a method of Conversation learning based on the flow of human utterance patterns and its related perceptual information. Finally, we show experimental results of the proposed method, and discuss the future direction on this research.

  • RVSP - Life Log Visualization System Based on Informationally Structured Space for Supporting Elderly People
    2013 Second International Conference on Robot Vision and Signal Processing, 2013
    Co-Authors: Yuri Yoshihara, Dalai Tang, Naoyuki Kubota
    Abstract:

    This paper proposes human behavior perception compound between passive perception and active perception. Human behavior is stored in a database for creating the life log to realize visualization System for supporting elderly people using iPad. First, we discuss the life log System configuration based on information ally structured space. We apply sensor network and smart phone for measuring human behavior to realize passive perception, and we also apply Conversation System for conducting communication between robot partner and human to realize active perception. Next, we explain the database System that constructs information ally structured space. The cloud database is used to share the elderly people's life log information with the elderly people's family and caregivers through the visualization System. Finally, we discuss the usability of the Visualization System through experimental results.

  • Computational intelligence for human-friendly robot partners based on multi-modal communication
    The 1st IEEE Global Conference on Consumer Electronics 2012, 2012
    Co-Authors: Yuichiro Toda, Naoyuki Kubota
    Abstract:

    This paper discusses the multi-modal communication for robot partners based on computational intelligence in informationally structured space. First, we explain recognition methods of touch interface, voice recognition, human detection, gesture recognition used in the multi-modal communication. Furthermore, we propose a Conversation System to realize the multi-modal communication with a person. Finally, we show several experimental results of the proposed method, and discuss the future direction on this research.

  • Multimodal Communication for Human-Friendly Robot Partners in Informationally Structured Space
    IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2012
    Co-Authors: Naoyuki Kubota, Yuichiro Toda
    Abstract:

    This paper proposes a multimodal communication method for human-friendly robot partners based on various types of sensors. First, we explain informationally structured space to extend the cognitive capabilities of robot partners based on environmental Systems. Next, we discuss the suitable measurement range for recognition technologies of touch interface, voice recognition, human detection, gesture recognition, and others. Based on the suitable measurement ranges, we propose an integration method to estimate human behaviors based on the human detection using color image and 3-D distance information, and gesture recognition by the multilayered spiking neural network using the time series of human-hand positions. Furthermore, we propose a Conversation System to realize the multimodal communication with a person. Finally, we show several experimental results of the proposed method, and discuss the future direction of this research.

Yiping Song - One of the best experts on this subject based on the ideXlab platform.

  • IJCAI - An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
    Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
    Co-Authors: Yiping Song, Dongyan Zhao, Ming Zhang, Jian-yun Nie, Rui Yan
    Abstract:

     Human-computer Conversation Systems have attracted much attention in Natural Language Processing. Conversation Systems can be roughly divided into two categories: retrieval-based and generation-based Systems. Retrieval Systems search a user-issued utterance (namely a query ) in a large Conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based Conversation System. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble System outperforms each single module by a large margin.

  • learning to respond with deep neural networks for retrieval based human computer Conversation System
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2016
    Co-Authors: Rui Yan, Yiping Song
    Abstract:

    To establish an automatic Conversation System between humans and computers is regarded as one of the most hardcore problems in computer science, which involves interdisciplinary techniques in information retrieval, natural language processing, artificial intelligence, etc. The challenges lie in how to respond so as to maintain a relevant and continuous Conversation with humans. Along with the prosperity of Web 2.0, we are now able to collect extremely massive Conversational data, which are publicly available. It casts a great opportunity to launch automatic Conversation Systems. Owing to the diversity of Web resources, a retrieval-based Conversation System will be able to find at least some responses from the massive repository for any user inputs. Given a human issued message, i.e., query, our System would provide a reply after adequate training and learning of how to respond. In this paper, we propose a retrieval-based Conversation System with the deep learning-to-respond schema through a deep neural network framework driven by web data. The proposed model is general and unified for different Conversation scenarios in open domain. We incorporate the impact of multiple data inputs, and formulate various features and factors with optimization into the deep learning framework. In the experiments, we investigate the effectiveness of the proposed deep neural network structures with better combinations of all different evidence. We demonstrate significant performance improvement against a series of standard and state-of-art baselines in terms of p@1, MAP, nDCG, and MRR for Conversational purposes.

  • SIGIR - Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System
    Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, 2016
    Co-Authors: Rui Yan, Yiping Song
    Abstract:

    To establish an automatic Conversation System between humans and computers is regarded as one of the most hardcore problems in computer science, which involves interdisciplinary techniques in information retrieval, natural language processing, artificial intelligence, etc. The challenges lie in how to respond so as to maintain a relevant and continuous Conversation with humans. Along with the prosperity of Web 2.0, we are now able to collect extremely massive Conversational data, which are publicly available. It casts a great opportunity to launch automatic Conversation Systems. Owing to the diversity of Web resources, a retrieval-based Conversation System will be able to find at least some responses from the massive repository for any user inputs. Given a human issued message, i.e., query, our System would provide a reply after adequate training and learning of how to respond. In this paper, we propose a retrieval-based Conversation System with the deep learning-to-respond schema through a deep neural network framework driven by web data. The proposed model is general and unified for different Conversation scenarios in open domain. We incorporate the impact of multiple data inputs, and formulate various features and factors with optimization into the deep learning framework. In the experiments, we investigate the effectiveness of the proposed deep neural network structures with better combinations of all different evidence. We demonstrate significant performance improvement against a series of standard and state-of-art baselines in terms of p@1, MAP, nDCG, and MRR for Conversational purposes.

Dongyan Zhao - One of the best experts on this subject based on the ideXlab platform.

  • Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce
    arXiv: Computation and Language, 2019
    Co-Authors: Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan
    Abstract:

    Information-seeking Conversation System aims at satisfying the information needs of users through Conversations. Text matching between a user query and a pre-collected question is an important part of the information-seeking Conversation in E-commerce. In the practical scenario, a sort of questions always correspond to a same answer. Naturally, these questions can form a bag. Learning the matching between user query and bag directly may improve the Conversation performance, denoted as query-bag matching. Inspired by such opinion, we propose a query-bag matching model which mainly utilizes the mutual coverage between query and bag and measures the degree of the content in the query mentioned by the bag, and vice verse. In addition, the learned bag representation in word level helps find the main points of a bag in a fine grade and promotes the query-bag matching performance. Experiments on two datasets show the effectiveness of our model.

  • CIKM - Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce
    Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019
    Co-Authors: Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan
    Abstract:

    Information-seeking Conversation System aims at satisfying the information needs of users through Conversations. Text matching between a user query and a pre-collected question is an important part of the information-seeking Conversation in E-commerce. In the practical scenario, a sort of questions always correspond to a same answer. Naturally, these questions can form a bag. Learning the matching between user query and bag directly may improve the Conversation performance, denoted as query-bag matching. Inspired by such opinion, we propose a query-bag matching model which mainly utilizes the mutual coverage between query and bag and measures the degree of the content in the query mentioned by the bag, and vice verse. In addition, the learned bag representation in word level helps find the main points of a bag in a fine grade and promotes the query-bag matching performance. Experiments on two datasets show the effectiveness of our model.

  • WWW (Companion Volume) - A NeuRetrieval Model for Human-Computer Conversations
    Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018
    Co-Authors: Rui Yan, Dongyan Zhao
    Abstract:

    To establish an automatic Conversation System between human and computer is regarded as one of the most hardcore problems in computer science. It requires interdisciplinary techniques of information retrieval, natural language processing, data management as well as artificial intelligence. The arrival of big data era reveals the feasibility to create a Conversation System empowered by data-driven approaches. Now we are able to collect extremely large Conversational data on Web, and organize them to launch a human-computer Conversation System. Owing to the diversity of Web resources available, a retrieval-based Conversation System will be able to find at least some responses from the massive data repository for any user inputs. Given a human issued utterance, i.e., a query, a retrieval-based Conversation System will search for appropriate replies, conduct a relevance ranking, and then output the highly relevant one as the response. In this paper, we propose a novel retrieval model named NeuRetrieval for short text understanding, representation and semantic matching. The proposed model is general and unified for both single-turn and multi-turn Conversation scenarios in open domain. In the experiments, we investigate the effectiveness of the proposed deep neural network model for human-computer Conversations. We demonstrate performance improvement against a series of baseline methods in several evaluation metrics. In contrast with previously proposed methods, NeuRetrieval is tailored for Conversation scenarios and demonstrated to be more effective.

  • IJCAI - An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
    Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
    Co-Authors: Yiping Song, Dongyan Zhao, Ming Zhang, Jian-yun Nie, Rui Yan
    Abstract:

     Human-computer Conversation Systems have attracted much attention in Natural Language Processing. Conversation Systems can be roughly divided into two categories: retrieval-based and generation-based Systems. Retrieval Systems search a user-issued utterance (namely a query ) in a large Conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based Conversation System. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble System outperforms each single module by a large margin.

  • joint learning of response ranking and next utterance suggestion in human computer Conversation System
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017
    Co-Authors: Rui Yan, Dongyan Zhao, E Weinan
    Abstract:

    Conversation Systems are of growing importance since they enable an easy interaction interface between humans and computers: using natural languages. To build a Conversation System with adequate intelligence is challenging, and requires abundant resources including an acquisition of big data and interdisciplinary techniques, such as information retrieval and natural language processing. Along with the prosperity of Web 2.0, the massive data available greatly facilitate data-driven methods such as deep learning for human-computer Conversation Systems. Owing to the diversity of Web resources, a retrieval-based Conversation System will come up with at least some results from the immense repository for any user inputs. Given a human issued message, i.e., query, a traditional Conversation System would provide a response after adequate training and learning of how to respond. In this paper, we propose a new task for Conversation Systems: joint learning of response ranking featured with next utterance suggestion. We assume that the new Conversation mode is more proactive and keeps user engaging. We examine the assumption in experiments. Besides, to address the joint learning task, we propose a novel Dual-LSTM Chain Model to couple response ranking and next utterance suggestion simultaneously. From the experimental results, we demonstrate the usefulness of the proposed task and the effectiveness of the proposed model.

Nestor Garay - One of the best experts on this subject based on the ideXlab platform.

  • Applying the Affinto Ontology to Develop a Text-Based Emotional Conversation System
    2011
    Co-Authors: Idoia Cearreta, Nestor Garay
    Abstract:

    With the recent spread of computing Systems the need to enhance interactions between users and Systems is evident. Conversation Systems have a key role to play in achieving this. However, further efforts are needed to enhance Conversation Systems that use text to interact with users. This paper presents a text Conversation System that includes user emotion recognition and generation, with the aim of achieving a more natural communication. The Affinto ontology is used to perform these tasks.

  • INTERACT (4) - Applying the affinto ontology to develop a text-based emotional Conversation System
    Human-Computer Interaction – INTERACT 2011, 2011
    Co-Authors: Idoia Cearreta, Nestor Garay
    Abstract:

    With the recent spread of computing Systems the need to enhance interactions between users and Systems is evident. Conversation Systems have a key role to play in achieving this. However, further efforts are needed to enhance Conversation Systems that use text to interact with users. This paper presents a text Conversation System that includes user emotion recognition and generation, with the aim of achieving a more natural communication. The Affinto ontology is used to perform these tasks.