Filters








20,846 Hits in 9.9 sec

End-to-end optimization of goal-driven and visually grounded dialogue systems

Florian Strub, Harm de Vries, Jérémie Mary, Bilal Piot, Aaron Courville, Olivier Pietquin
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning.  ...  In this paper, we introduce a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues, based on the policy gradient algorithm.  ...  Acknowledgements The authors would like to acknowledge the environment provided by the SequeL labs.  ... 
doi:10.24963/ijcai.2017/385 dblp:conf/ijcai/StrubVMPCP17 fatcat:z2pepajdjrdzblmf6pojkjnt3a

End-to-end optimization of goal-driven and visually grounded dialogue systems [article]

Florian Strub and Harm de Vries and Jeremie Mary and Bilal Piot and Aaron Courville and Olivier Pietquin
2017 arXiv   pre-print
In this paper, we introduce a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues, based on the policy gradient algorithm.  ...  End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning.  ...  Acknowledgement The authors would like to acknowledge the stimulating environment provided by the SequeL labs.  ... 
arXiv:1703.05423v1 fatcat:c3g4futw7jdzppp4v2p3hn46em

A system for interactive learning in dialogue with a tutor

D. Skocaj, M. Kristan, A. Vrecko, M. Mahnic, M. Janicek, G. M. Kruijff, M. Hanheide, N. Hawes, T. Keller, M. Zillich, Kai Zhou
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this paper we present representations and mechanisms that facilitate continuous learning of visual concepts in dialogue with a tutor and show the implemented robot system.  ...  We present how beliefs about the world are created by processing visual and linguistic information and show how they are used for planning system behaviour with the aim at satisfying its internal drive  ...  We extend Thomason and Stone's abductive account of language understanding, planning and production [14] , in which agents actively monitor and maintain common ground, and to this end they attempt to  ... 
doi:10.1109/iros.2011.6048563 fatcat:atrniirmx5hqnei6hi5wyc65we

A system for interactive learning in dialogue with a tutor

Danijel Skocaj, Matej Kristan, Alen Vrecko, Marko Mahnic, Miroslav Janicek, Geert-Jan M. Kruijff, Marc Hanheide, Nick Hawes, Thomas Keller, Michael Zillich, Kai Zhou
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this paper we present representations and mechanisms that facilitate continuous learning of visual concepts in dialogue with a tutor and show the implemented robot system.  ...  We present how beliefs about the world are created by processing visual and linguistic information and show how they are used for planning system behaviour with the aim at satisfying its internal drive  ...  We extend Thomason and Stone's abductive account of language understanding, planning and production [14] , in which agents actively monitor and maintain common ground, and to this end they attempt to  ... 
doi:10.1109/iros.2011.6094926 dblp:conf/iros/SkocajKVMJKHHKZZ11 fatcat:h37ia26ubjaxlnojnmgl5hqvaa

A dynamic goal adapted task oriented dialogue agent

Abhisek Tiwari, Tulika Saha, Sriparna Saha, Shubhashis Sengupta, Anutosh Maitra, Roshni Ramnani, Pushpak Bhattacharyya, Weinan Zhang
2021 PLoS ONE  
Purpose Existing virtual agents (VAs) present in dialogue systems are either information retrieval based or static goal-driven.  ...  A Dynamic Goal Driven Dialogue Agent (DGDVA) has been developed by incorporating a Dynamic Goal Driven Module (GDM) on top of a deep reinforcement learning based dialogue manager.  ...  An end to end neural dialogue system has been proposed in [22] to deal with drawbacks of a modularized task-oriented dialogue system.  ... 
doi:10.1371/journal.pone.0249030 pmid:33793633 fatcat:65qjx6rxpbaybn6fovyhmrwm5i

Data-Driven Dialogue Systems for Social Agents [chapter]

Kevin K. Bowden, Shereen Oraby, Amita Misra, Jiaqi Wu, Stephanie Lukin, Marilyn Walker
2018 Lecture Notes in Electrical Engineering  
To facilitate research in this area, we have carried out a wide survey of publicly available datasets suitable for data-driven learning of dialogue systems.  ...  We discuss important characteristics of these datasets, how they can be used to learn various components of a dialogue system, and their other potential uses.  ...  Early versions of the manuscript benefited greatly from the proofreading of Melanie Lyman-Abramovitch, and later versions were extensively revised by Genevieve Fried and Nicolas Angelard-Gontier.  ... 
doi:10.1007/978-3-319-92108-2_6 fatcat:nrqzpujukreojdkkusbzy4uniy

Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review [article]

Hao Wang, Bin Guo, Yating Zeng, Yasan Ding, Chen Qiu, Ying Zhang, Lina Yao, Zhiwen Yu
2022 arXiv   pre-print
Consequently, Visual Context Augmented Dialogue System (VAD), which has the potential to communicate with humans by perceiving and understanding multimodal information (i.e., visual context in images or  ...  For depicting the development of VAD, we first characterize the concepts and unique features of VAD, and then present its generic system architecture to illustrate the system workflow.  ...  ACKNOWLEDGMENTS This work was partially supported by the National Science Fund for Distinguished Young Scholars (62025205), and the National Natural Science Foundation of China (No. 62032020, 61960206008  ... 
arXiv:2207.00782v1 fatcat:a57laj75xfa43gg4hjvxdh4c4i

A Survey of Available Corpora for Building Data-Driven Dialogue Systems [article]

Iulian Vlad Serban, Ryan Lowe, Peter Henderson, Laurent Charlin, Joelle Pineau
2017 arXiv   pre-print
To facilitate research in this area, we have carried out a wide survey of publicly available datasets suitable for data-driven learning of dialogue systems.  ...  In the area of dialogue systems, the trend is less obvious, and most practical systems are still built through significant engineering and expert knowledge.  ...  Early versions of the manuscript benefited greatly from the proofreading of Melanie Lyman-Abramovitch, and later versions were extensively revised by Genevieve Fried and Nicolas Angelard-Gontier.  ... 
arXiv:1512.05742v3 fatcat:lh34cnbvefcfxp2qwxfyiuuwhm

Neural Approaches to Conversational AI

Jianfeng Gao, Michel Galley, Lihong Li
2019 Foundations and Trends in Information Retrieval  
Figure 1 . 2 : 12 Two architectures of dialogue systems for (Top) traditional task-oriented dialogue and (Bottom) fully data-driven dialogue.  ...  dialogue agents, focusing on applying deep reinforcement learning to dialogue management. • Chapter 5 describes social chatbots, focusing on fully data-driven neural approaches to end-to-end generation  ... 
doi:10.1561/1500000074 fatcat:5ou22zmnq5ghjnkqmbxbfkurhu

Converse, Focus and Guess – Towards Multi-Document Driven Dialogue [article]

Han Liu, Caixia Yuan, Xiaojie Wang, Yushu Yang, Huixing Jiang, Zhongyuan Wang
2021 arXiv   pre-print
Then it tracks dialogue state by detecting evolvement of document belief and attribute belief, and finally optimizes dialogue policy in principle of entropy decreasing and reward increasing, which is expected  ...  To benchmark progress, we introduce a new dataset of GuessMovie, which contains 16,881 documents, each describing a movie, and associated 13,434 dialogues. Further, we propose the MD3 model.  ...  The research is supported in part by the Natural Science Foundation of China (Grant No. 62076032) and National Key Research and Development Program of China (Grant No. 2020YFF0305302).  ... 
arXiv:2102.02435v1 fatcat:y27it2g3i5ed5msmobdl626fz4

The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings

Yanchao Yu, Arash Eshghi, Gregory Mills, Oliver Lemon
2017 Proceedings of the Sixth Workshop on Vision and Language  
We motivate and describe a new freely available human-human dialogue dataset for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner.  ...  Finally, we train and evaluate a Reinforcement Learning dialogue control agent for learning visually grounded word meanings, trained from the BURCHAK corpus.  ...  Acknowledgments This research is supported by the EPSRC, under grant number EP/M01553X/1 (BABBLE project 3 ), and by the European Union's Horizon 2020 research and innovation programme under grant agreement  ... 
doi:10.18653/v1/w17-2001 dblp:conf/acl-vl/YuEML17 fatcat:p6o6moep25doplvtrw736wgzti

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models [article]

Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, Joelle Pineau
2016 arXiv   pre-print
In support of this goal, we extend the recently proposed hierarchical recurrent encoder-decoder neural network to the dialogue domain, and demonstrate that this model is competitive with state-of-the-art  ...  We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models.  ...  Acknowledgements The authors acknowledge IBM Research, NSERC, Canada Research Chairs, Nuance Foundation, CIFAR and Compute Canada for funding and resources.  ... 
arXiv:1507.04808v3 fatcat:sw2dgffakvchphom64e2ebg43y

The Rapidly Changing Landscape of Conversational Agents [article]

Vinayak Mathur, Arpit Singh
2018 arXiv   pre-print
Conversational agents have become ubiquitous, ranging from goal-oriented systems for helping with reservations to chit-chat models found in modern virtual assistants.  ...  We look at some of the pioneering work that defined the field and gradually move to the current state-of-the-art models.  ...  Dialogue systems can be divided into goal-driven systems, such as technical support services, booking systems, and querying systems.  ... 
arXiv:1803.08419v2 fatcat:5huy2e6tmbexlfoampcdy6zhw4

CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication

Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, Devi Parikh
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In this work, we propose a goal-driven collaborative task that combines language, perception, and action.  ...  Our game is grounded in a virtual world that contains movable clip art objects. The game involves two players: a Teller and a Drawer.  ...  Lawrence Zitnick for helpful comments and discussion.  ... 
doi:10.18653/v1/p19-1651 dblp:conf/acl/KimKCRZTBP19 fatcat:tl2ixoqdh5bt7bj3ftdj4rh6fe

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

Iulian Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, Joelle Pineau
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In support of this goal, we extend the recently proposed hierarchical recurrent encoder-decoder neural network to the dialogue domain, and demonstrate that this model is competitive with state-of-the-art  ...  We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models.  ...  Acknowledgements The authors acknowledge IBM Research, NSERC, Canada Research Chairs, CIFAR and Compute Canada for funding and resources.  ... 
doi:10.1609/aaai.v30i1.9883 fatcat:2yb3jdv3hjbkte35zmwizngugi
« Previous Showing results 1 — 15 out of 20,846 results