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.
Beschreibung
Building End-To-End Dialogue Systems Using Generative Hierarchical
Neural Network Models
%0 Generic
%1 serban2015building
%A Serban, Iulian V.
%A Sordoni, Alessandro
%A Bengio, Yoshua
%A Courville, Aaron
%A Pineau, Joelle
%D 2015
%K attention-rnn nn rnn
%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{serban2015building,
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 = {2016-12-03T03:26:50.000+0100},
author = {Serban, Iulian V. and Sordoni, Alessandro and Bengio, Yoshua and Courville, Aaron and Pineau, Joelle},
biburl = {https://www.bibsonomy.org/bibtex/2f93a2fa38c2b14faa1de5fd52243e0f7/jkan},
description = {Building End-To-End Dialogue Systems Using Generative Hierarchical
Neural Network Models},
interhash = {22dfc8355f1fb003664427c4251aa8c3},
intrahash = {f93a2fa38c2b14faa1de5fd52243e0f7},
keywords = {attention-rnn nn rnn},
note = {cite arxiv:1507.04808Comment: 8 pages with references; Published in AAAI 2016 (Special Track on Cognitive Systems)},
timestamp = {2016-12-03T03:26:50.000+0100},
title = {Building End-To-End Dialogue Systems Using Generative Hierarchical
Neural Network Models},
url = {http://arxiv.org/abs/1507.04808},
year = 2015
}