@inproceedings{agarwal-etal-2018-improving,
title = "Improving Context Modelling in Multimodal Dialogue Generation",
author = "Agarwal, Shubham and
Du{\v{s}}ek, Ond{\v{r}}ej and
Konstas, Ioannis and
Rieser, Verena",
editor = "Krahmer, Emiel and
Gatt, Albert and
Goudbeek, Martijn",
booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
month = nov,
year = "2018",
address = "Tilburg University, The Netherlands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6514",
doi = "10.18653/v1/W18-6514",
pages = "129--134",
abstract = "In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system{'}s output.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2018-improving">
<titleInfo>
<title>Improving Context Modelling in Multimodal Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">Krahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Goudbeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tilburg University, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system’s output.</abstract>
<identifier type="citekey">agarwal-etal-2018-improving</identifier>
<identifier type="doi">10.18653/v1/W18-6514</identifier>
<location>
<url>https://aclanthology.org/W18-6514</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>129</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Context Modelling in Multimodal Dialogue Generation
%A Agarwal, Shubham
%A Dušek, Ondřej
%A Konstas, Ioannis
%A Rieser, Verena
%Y Krahmer, Emiel
%Y Gatt, Albert
%Y Goudbeek, Martijn
%S Proceedings of the 11th International Conference on Natural Language Generation
%D 2018
%8 November
%I Association for Computational Linguistics
%C Tilburg University, The Netherlands
%F agarwal-etal-2018-improving
%X In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system’s output.
%R 10.18653/v1/W18-6514
%U https://aclanthology.org/W18-6514
%U https://doi.org/10.18653/v1/W18-6514
%P 129-134
Markdown (Informal)
[Improving Context Modelling in Multimodal Dialogue Generation](https://aclanthology.org/W18-6514) (Agarwal et al., INLG 2018)
ACL
- Shubham Agarwal, Ondřej Dušek, Ioannis Konstas, and Verena Rieser. 2018. Improving Context Modelling in Multimodal Dialogue Generation. In Proceedings of the 11th International Conference on Natural Language Generation, pages 129–134, Tilburg University, The Netherlands. Association for Computational Linguistics.