Filters








992 Hits in 6.0 sec

A Network-based End-to-End Trainable Task-oriented Dialogue System [article]

Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young
2017 arXiv   pre-print
In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz  ...  Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve  ...  In this work, we propose a neural network-based model for task-oriented dialogue systems by balancing the strengths and the weaknesses of the two research communities: the model is end-to-end trainable  ... 
arXiv:1604.04562v3 fatcat:toyhgoy3gfctjdyukr4mfcnpbe

A Network-based End-to-End Trainable Task-oriented Dialogue System

Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes, Steve Young
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
In this work we introduce a neural network-based text-in, textout end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz  ...  This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand.  ...  In this work, we propose a neural network-based model for task-oriented dialogue systems by balancing the strengths and the weaknesses of the two research communities: the model is end-to-end trainable  ... 
doi:10.18653/v1/e17-1042 dblp:conf/eacl/Rojas-BarahonaG17 fatcat:ookrim7vdng3lj2fl45estnrhy

Comparison of an End-to-end Trainable Dialogue System with a Modular Statistical Dialogue System

Norbert Braunschweiler, Alexandros Papangelis
2018 Interspeech 2018  
This paper presents a comparison of two dialogue systems: one is end-to-end trainable and the other uses a more traditional, modular architecture.  ...  End-to-end trainable dialogue systems recently attracted a lot of attention because they offer several advantages over traditional systems.  ...  The end-to-end system (E2E) evaluated here, belongs to the task-oriented family. It is based on the system presented in [8] which is an end-to-end trainable, neural network driven dialogue system.  ... 
doi:10.21437/interspeech.2018-1679 dblp:conf/interspeech/BraunschweilerP18 fatcat:6o4oijbotzf77km4x7ju5du2s4

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning [article]

Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, Larry Heck
2017 arXiv   pre-print
In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL).  ...  The system is able to track dialogue state, interface with knowledge bases, and incorporate query results into agent's responses to successfully complete task-oriented dialogues.  ...  In this work, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep RL.  ... 
arXiv:1711.10712v2 fatcat:rhelcmq37ffqrlczqesx3vqvm4

Key-Value Retrieval Networks for Task-Oriented Dialogue [article]

Mihail Eric, Christopher D. Manning
2017 arXiv   pre-print
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.  ...  The model is end-to-end differentiable and does not need to explicitly model dialogue state or belief trackers.  ...  Acknowledgments The authors wish to thank He He, Peng Qi, Urvashi Khandelwal, and Reid Pryzant for their valuable feedback and insights.  ... 
arXiv:1705.05414v2 fatcat:h4d3aoforzdgdbhix2bqc3rdlm

Key-Value Retrieval Networks for Task-Oriented Dialogue

Mihail Eric, Lakshmi Krishnan, Francois Charette, Christopher D. Manning
2017 Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue  
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.  ...  The model is end-to-end differentiable and does not need to explicitly model dialogue state or belief trackers.  ...  Acknowledgments The authors wish to thank He He, Peng Qi, Urvashi Khandelwal, and Reid Pryzant for their valuable feedback and insights.  ... 
doi:10.18653/v1/w17-5506 dblp:conf/sigdial/EricKCM17 fatcat:fglbnktosjdrvpd2xdlgn6gh4m

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems [article]

Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, Larry Heck
2018 arXiv   pre-print
We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method.  ...  In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions.  ...  Recent efforts have been made in designing end-to-end solutions for task-oriented dialogues, inspired by the success of encoder-decoder based neural network models in non-task-oriented conversational systems  ... 
arXiv:1804.06512v1 fatcat:umntnko5gfaczkbfjvhbze6pnq

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

Bing Liu, Gokhan Tür, Dilek Hakkani-Tür, Pararth Shah, Larry Heck
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
We design a neural network based task-oriented dialogue agent that can be optimized end-toend with the proposed learning method.  ...  In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions.  ...  Recent efforts have been made in designing end-to-end solutions for task-oriented dialogues, inspired by the success of encoder-decoder based neural network models in non-task-oriented conversational systems  ... 
doi:10.18653/v1/n18-1187 dblp:conf/naacl/LiuTHSH18 fatcat:vuhvrw6xgzdcpp3b5fdksg6jpq

A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue [article]

Mihail Eric, Christopher D. Manning
2017 arXiv   pre-print
In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented agents usually explicitly model user intent and belief states.  ...  Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics.  ...  Acknowledgments The authors wish to thank the reviewers, Lakshmi Krishnan, Francois Charette, and He He for their valuable feedback and insights.  ... 
arXiv:1701.04024v3 fatcat:uk5wdjm5d5hwvnzcsssotkpczm

A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue

Mihail Eric, Christopher Manning
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers  
In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented agents usually explicitly model user intent and belief states.  ...  Task-oriented dialogue focuses on conversational agents that participate in dialogues with user goals on domain-specific topics.  ...  Acknowledgments The authors wish to thank the reviewers, Lakshmi Krishnan, Francois Charette, and He He for their valuable feedback and insights.  ... 
doi:10.18653/v1/e17-2075 dblp:conf/eacl/ManningE17 fatcat:mklphur66bhfza7537t4ngi6hi

A Survey on Dialogue Systems: Recent Advances and New Frontiers [article]

Hongshen Chen, Xiaorui Liu, Dawei Yin, Jiliang Tang
2018 arXiv   pre-print
In particular, we generally divide existing dialogue systems into task-oriented and non-task-oriented models, then detail how deep learning techniques help them with representative algorithms and finally  ...  For dialogue systems, deep learning can leverage a massive amount of data to learn meaningful feature representations and response generation strategies, while requiring a minimum amount of hand-crafting  ...  [97] and [7] introduced a network-based end-to-end trainable task-oriented dialogue system, which treated dialogue system learning as the problem of learning a mapping from dialogue histories to system  ... 
arXiv:1711.01731v3 fatcat:6wuovcynqbhlzmuorchn4mn6ma

DeepPavlov: Open-Source Library for Dialogue Systems

Mikhail Burtsev, Alexander Seliverstov, Rafael Airapetyan, Mikhail Arkhipov, Dilyara Baymurzina, Nickolay Bushkov, Olga Gureenkova, Taras Khakhulin, Yuri Kuratov, Denis Kuznetsov, Alexey Litinsky, Varvara Logacheva (+8 others)
2018 Proceedings of ACL 2018, System Demonstrations  
This creates a demand for tools that speed up prototyping of featurerich dialogue systems. An open-source library DeepPavlov is tailored for development of conversational agents.  ...  Sequence-to-sequence chit-chat skill, question answering skill or task-oriented skill can be assembled from components provided in the library.  ...  That makes easier for developers to fit trainable parts of the system to the task at hand or add custom ML models.  ... 
doi:10.18653/v1/p18-4021 dblp:conf/acl/BurtsevSAABBGKK18 fatcat:2hzjbzc5zjgnjcejim7vjz7e4y

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks [article]

Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Ying Zhang
2019 arXiv   pre-print
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans.  ...  To handle this problem, memory networks are usually a great choice and a promising way.  ...  By adding a knowledge base module, recent works (Ghazvininejad et al., 2018; have shown the possibility of training an end-to-end task-oriented dialogue system on the sequence to sequence architecture  ... 
arXiv:1909.11287v1 fatcat:lilx5hyyljej7janwebybltzau

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Yin Zhang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans.  ...  To handle this problem, memory networks are usually a great choice and a promising way.  ...  By adding a knowledge base module, recent works (Ghazvininejad et al., 2018; have shown the possibility of training an end-to-end task-oriented dialogue system on the sequence to sequence architecture  ... 
doi:10.18653/v1/d19-1463 dblp:conf/emnlp/LinHJCZ19 fatcat:djelamkro5cpvi3qo5zpuftfne

Deep Learning for Dialogue Systems

Yun-Nung Chen, Asli Celikyilmaz, Dilek Hakkani-Tür
2017 Proceedings of ACL 2017, Tutorial Abstracts  
However, how to successfully apply deep learning based approaches to a dialogue system is still challenging.  ...  In the past decade, goal-oriented spoken dialogue systems have been the most prominent component in today's virtual personal assistants.  ...  and Bordes and Weston (2016) introduced a network-based end-to-end trainable task-oriented dialogue system, which treated dialogue system learning as the problem of learning a mapping from dialogue histories  ... 
doi:10.18653/v1/p17-5004 dblp:conf/acl/ChenCH17 fatcat:eyltpy5guna6bfsczav3vji7x4
« Previous Showing results 1 — 15 out of 992 results