This paper presents an end-to-end learning framework for task-completion
neural dialogue systems, which leverages supervised and reinforcement learning
with various deep-learning models. The system is able to interface with a
structured database, and interact with users for assisting them to access
information and complete tasks such as booking movie tickets. Our experiments
in a movie-ticket booking domain show the proposed system outperforms a
modular-based dialogue system and is more robust to noise produced by other
components in the system.
Beschreibung
End-to-End Task-Completion Neural Dialogue Systems
%0 Generic
%1 li2017endtoend
%A Li, Xuijun
%A Chen, Yun-Nung
%A Li, Lihong
%A Gao, Jianfeng
%D 2017
%K chatbot machinelearning nlp
%T End-to-End Task-Completion Neural Dialogue Systems
%U http://arxiv.org/abs/1703.01008
%X This paper presents an end-to-end learning framework for task-completion
neural dialogue systems, which leverages supervised and reinforcement learning
with various deep-learning models. The system is able to interface with a
structured database, and interact with users for assisting them to access
information and complete tasks such as booking movie tickets. Our experiments
in a movie-ticket booking domain show the proposed system outperforms a
modular-based dialogue system and is more robust to noise produced by other
components in the system.
@misc{li2017endtoend,
abstract = {This paper presents an end-to-end learning framework for task-completion
neural dialogue systems, which leverages supervised and reinforcement learning
with various deep-learning models. The system is able to interface with a
structured database, and interact with users for assisting them to access
information and complete tasks such as booking movie tickets. Our experiments
in a movie-ticket booking domain show the proposed system outperforms a
modular-based dialogue system and is more robust to noise produced by other
components in the system.},
added-at = {2017-03-09T03:45:50.000+0100},
author = {Li, Xuijun and Chen, Yun-Nung and Li, Lihong and Gao, Jianfeng},
biburl = {https://www.bibsonomy.org/bibtex/292e1cfc917818f928c9ac574f16d75c5/winterdawn},
description = {End-to-End Task-Completion Neural Dialogue Systems},
interhash = {44a837ed11c7744860bb4eec121fb3fc},
intrahash = {92e1cfc917818f928c9ac574f16d75c5},
keywords = {chatbot machinelearning nlp},
note = {cite arxiv:1703.01008},
timestamp = {2017-03-09T03:45:50.000+0100},
title = {End-to-End Task-Completion Neural Dialogue Systems},
url = {http://arxiv.org/abs/1703.01008},
year = 2017
}