@inproceedings{zhang-etal-2018-multimodal,
title = "Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog",
author = "Zhang, Jiaping and
Zhao, Tiancheng and
Yu, Zhou",
editor = "Komatani, Kazunori and
Litman, Diane and
Yu, Kai and
Papangelis, Alex and
Cavedon, Lawrence and
Nakano, Mikio",
booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5015",
doi = "10.18653/v1/W18-5015",
pages = "140--150",
abstract = "Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI) (Winograd, 1972). Extensive research has focused on vision-to-language generation, however, limited research has touched on combining these two modalities in a goal-driven dialog context. We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog. The framework jointly learns the multimodal dialog state representation and the hierarchical dialog policy to improve both dialog task success and efficiency. We also propose a new technique, state adaptation, to integrate context awareness in the dialog state representation. We evaluate the proposed framework and the state adaptation technique in an image guessing game and achieve promising results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2018-multimodal">
<titleInfo>
<title>Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaping</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiancheng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Cavedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI) (Winograd, 1972). Extensive research has focused on vision-to-language generation, however, limited research has touched on combining these two modalities in a goal-driven dialog context. We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog. The framework jointly learns the multimodal dialog state representation and the hierarchical dialog policy to improve both dialog task success and efficiency. We also propose a new technique, state adaptation, to integrate context awareness in the dialog state representation. We evaluate the proposed framework and the state adaptation technique in an image guessing game and achieve promising results.</abstract>
<identifier type="citekey">zhang-etal-2018-multimodal</identifier>
<identifier type="doi">10.18653/v1/W18-5015</identifier>
<location>
<url>https://aclanthology.org/W18-5015</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>140</start>
<end>150</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
%A Zhang, Jiaping
%A Zhao, Tiancheng
%A Yu, Zhou
%Y Komatani, Kazunori
%Y Litman, Diane
%Y Yu, Kai
%Y Papangelis, Alex
%Y Cavedon, Lawrence
%Y Nakano, Mikio
%S Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F zhang-etal-2018-multimodal
%X Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI) (Winograd, 1972). Extensive research has focused on vision-to-language generation, however, limited research has touched on combining these two modalities in a goal-driven dialog context. We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog. The framework jointly learns the multimodal dialog state representation and the hierarchical dialog policy to improve both dialog task success and efficiency. We also propose a new technique, state adaptation, to integrate context awareness in the dialog state representation. We evaluate the proposed framework and the state adaptation technique in an image guessing game and achieve promising results.
%R 10.18653/v1/W18-5015
%U https://aclanthology.org/W18-5015
%U https://doi.org/10.18653/v1/W18-5015
%P 140-150
Markdown (Informal)
[Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog](https://aclanthology.org/W18-5015) (Zhang et al., SIGDIAL 2018)
ACL