@inproceedings{agarwal-etal-2020-history,
title = "History for Visual Dialog: Do we really need it?",
author = "Agarwal, Shubham and
Bui, Trung and
Lee, Joon-Young and
Konstas, Ioannis and
Rieser, Verena",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.728",
doi = "10.18653/v1/2020.acl-main.728",
pages = "8182--8197",
abstract = "Visual Dialogue involves {``}understanding{''} the dialogue history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to accurately generate the correct response. In this paper, we show that co-attention models which explicitly encode dialoh history outperform models that don{'}t, achieving state-of-the-art performance (72 {\%} NDCG on val set). However, we also expose shortcomings of the crowdsourcing dataset collection procedure, by showing that dialogue history is indeed only required for a small amount of the data, and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisdialConv) of the VisdialVal set and the benchmark NDCG of 63{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2020-history">
<titleInfo>
<title>History for Visual Dialog: Do we really need it?</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">Trung</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joon-Young</namePart>
<namePart type="family">Lee</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>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual Dialogue involves “understanding” the dialogue history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to accurately generate the correct response. In this paper, we show that co-attention models which explicitly encode dialoh history outperform models that don’t, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowdsourcing dataset collection procedure, by showing that dialogue history is indeed only required for a small amount of the data, and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisdialConv) of the VisdialVal set and the benchmark NDCG of 63%.</abstract>
<identifier type="citekey">agarwal-etal-2020-history</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.728</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.728</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>8182</start>
<end>8197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T History for Visual Dialog: Do we really need it?
%A Agarwal, Shubham
%A Bui, Trung
%A Lee, Joon-Young
%A Konstas, Ioannis
%A Rieser, Verena
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F agarwal-etal-2020-history
%X Visual Dialogue involves “understanding” the dialogue history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to accurately generate the correct response. In this paper, we show that co-attention models which explicitly encode dialoh history outperform models that don’t, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowdsourcing dataset collection procedure, by showing that dialogue history is indeed only required for a small amount of the data, and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisdialConv) of the VisdialVal set and the benchmark NDCG of 63%.
%R 10.18653/v1/2020.acl-main.728
%U https://aclanthology.org/2020.acl-main.728
%U https://doi.org/10.18653/v1/2020.acl-main.728
%P 8182-8197
Markdown (Informal)
[History for Visual Dialog: Do we really need it?](https://aclanthology.org/2020.acl-main.728) (Agarwal et al., ACL 2020)
ACL
- Shubham Agarwal, Trung Bui, Joon-Young Lee, Ioannis Konstas, and Verena Rieser. 2020. History for Visual Dialog: Do we really need it?. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8182–8197, Online. Association for Computational Linguistics.