O. Vinyals, и Q. Le. (2015)cite arxiv:1506.05869Comment: ICML Deep Learning Workshop 2015.
Аннотация
Conversational modeling is an important task in natural language
understanding and machine intelligence. Although previous approaches exist,
they are often restricted to specific domains (e.g., booking an airline ticket)
and require hand-crafted rules. In this paper, we present a simple approach for
this task which uses the recently proposed sequence to sequence framework. Our
model converses by predicting the next sentence given the previous sentence or
sentences in a conversation. The strength of our model is that it can be
trained end-to-end and thus requires much fewer hand-crafted rules. We find
that this straightforward model can generate simple conversations given a large
conversational training dataset. Our preliminary results suggest that, despite
optimizing the wrong objective function, the model is able to converse well. It
is able extract knowledge from both a domain specific dataset, and from a
large, noisy, and general domain dataset of movie subtitles. On a
domain-specific IT helpdesk dataset, the model can find a solution to a
technical problem via conversations. On a noisy open-domain movie transcript
dataset, the model can perform simple forms of common sense reasoning. As
expected, we also find that the lack of consistency is a common failure mode of
our model.
%0 Generic
%1 vinyals2015neural
%A Vinyals, Oriol
%A Le, Quoc
%D 2015
%K ai concersation deep learning network netze neural neuronale toread
%T A Neural Conversational Model
%U http://arxiv.org/abs/1506.05869
%X Conversational modeling is an important task in natural language
understanding and machine intelligence. Although previous approaches exist,
they are often restricted to specific domains (e.g., booking an airline ticket)
and require hand-crafted rules. In this paper, we present a simple approach for
this task which uses the recently proposed sequence to sequence framework. Our
model converses by predicting the next sentence given the previous sentence or
sentences in a conversation. The strength of our model is that it can be
trained end-to-end and thus requires much fewer hand-crafted rules. We find
that this straightforward model can generate simple conversations given a large
conversational training dataset. Our preliminary results suggest that, despite
optimizing the wrong objective function, the model is able to converse well. It
is able extract knowledge from both a domain specific dataset, and from a
large, noisy, and general domain dataset of movie subtitles. On a
domain-specific IT helpdesk dataset, the model can find a solution to a
technical problem via conversations. On a noisy open-domain movie transcript
dataset, the model can perform simple forms of common sense reasoning. As
expected, we also find that the lack of consistency is a common failure mode of
our model.
@misc{vinyals2015neural,
abstract = {Conversational modeling is an important task in natural language
understanding and machine intelligence. Although previous approaches exist,
they are often restricted to specific domains (e.g., booking an airline ticket)
and require hand-crafted rules. In this paper, we present a simple approach for
this task which uses the recently proposed sequence to sequence framework. Our
model converses by predicting the next sentence given the previous sentence or
sentences in a conversation. The strength of our model is that it can be
trained end-to-end and thus requires much fewer hand-crafted rules. We find
that this straightforward model can generate simple conversations given a large
conversational training dataset. Our preliminary results suggest that, despite
optimizing the wrong objective function, the model is able to converse well. It
is able extract knowledge from both a domain specific dataset, and from a
large, noisy, and general domain dataset of movie subtitles. On a
domain-specific IT helpdesk dataset, the model can find a solution to a
technical problem via conversations. On a noisy open-domain movie transcript
dataset, the model can perform simple forms of common sense reasoning. As
expected, we also find that the lack of consistency is a common failure mode of
our model.},
added-at = {2015-10-14T14:04:45.000+0200},
author = {Vinyals, Oriol and Le, Quoc},
biburl = {https://www.bibsonomy.org/bibtex/25ff361a9bea3e101dc12331b827fc969/hotho},
description = {A Neural Conversational Model},
interhash = {3b47e31a8cdd1ca3c45aa7e32b558808},
intrahash = {5ff361a9bea3e101dc12331b827fc969},
keywords = {ai concersation deep learning network netze neural neuronale toread},
note = {cite arxiv:1506.05869Comment: ICML Deep Learning Workshop 2015},
timestamp = {2015-11-02T09:43:35.000+0100},
title = {A Neural Conversational Model},
url = {http://arxiv.org/abs/1506.05869},
year = 2015
}