We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions. 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 neural language models and back-off n-gram models. We investigate the limitations of this and similar approaches, and show how its performance can be improved by bootstrapping the learning from a larger question-answer pair corpus and from pretrained word embeddings.
:C$\backslash$:/Users/MATIAS/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Serban et al. - 2015 - Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models.pdf:pdf
%0 Generic
%1 Serban2015
%A Serban, Iulian V.
%A Sordoni, Alessandro
%A Bengio, Yoshua
%A Courville, Aaron
%A Pineau, Joelle
%D 2015
%K audiovisual cinema traducción
%P 8
%T Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
%U http://arxiv.org/abs/1507.04808
%X We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions. 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 neural language models and back-off n-gram models. We investigate the limitations of this and similar approaches, and show how its performance can be improved by bootstrapping the learning from a larger question-answer pair corpus and from pretrained word embeddings.
@misc{Serban2015,
abstract = {We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions. 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 neural language models and back-off n-gram models. We investigate the limitations of this and similar approaches, and show how its performance can be improved by bootstrapping the learning from a larger question-answer pair corpus and from pretrained word embeddings.},
added-at = {2015-12-09T17:36:08.000+0100},
archiveprefix = {arXiv},
arxivid = {1507.04808},
author = {Serban, Iulian V. and Sordoni, Alessandro and Bengio, Yoshua and Courville, Aaron and Pineau, Joelle},
biburl = {https://www.bibsonomy.org/bibtex/2f93a2fa38c2b14faa1de5fd52243e0f7/cuevas.d},
eprint = {1507.04808},
file = {:C$\backslash$:/Users/MATIAS/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Serban et al. - 2015 - Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models.pdf:pdf},
interhash = {22dfc8355f1fb003664427c4251aa8c3},
intrahash = {f93a2fa38c2b14faa1de5fd52243e0f7},
keywords = {audiovisual cinema traducción},
mendeley-tags = {audiovisual,cinema,translation},
month = jul,
pages = 8,
timestamp = {2015-12-10T10:02:17.000+0100},
title = {{Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models}},
url = {http://arxiv.org/abs/1507.04808},
urldate = {2015-12-08},
year = 2015
}