@inproceedings{long-etal-2023-improving,
title = "Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning",
author = "Long, Yuxing and
Zhang, Huibin and
Hui, Binyuan and
Yang, Zhenglu and
Yuan, Caixia and
Wang, Xiaojie and
Huang, Fei and
Li, Yongbin",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.3",
pages = "15--24",
abstract = "To fulfill complex user requirements in a situated conversational scenario, the agent needs to conduct step-by-step multi-modal logic reasoning, which includes locating objects, querying information and searching objects. However, existing methods omit this multi-step procedure and therefore constitutes the risk of shortcuts when making predictions. For example, they may directly copy the information from the dialogue history or simply use the textual description without perform visual reasoning. To address this issue and further boost the system performance, we apply the dual process theory to plug a reasoner into the original transformer based model for step-by-step reasoning. When system 2 completes multi-step reasoning, its output is regarded as final prediction. Our proposed method achieved the 1st rank on the summing scores across all four DSTC-11 SIMMC 2.1 sub-tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2023-improving">
<titleInfo>
<title>Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxing</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huibin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyuan</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenglu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongbin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To fulfill complex user requirements in a situated conversational scenario, the agent needs to conduct step-by-step multi-modal logic reasoning, which includes locating objects, querying information and searching objects. However, existing methods omit this multi-step procedure and therefore constitutes the risk of shortcuts when making predictions. For example, they may directly copy the information from the dialogue history or simply use the textual description without perform visual reasoning. To address this issue and further boost the system performance, we apply the dual process theory to plug a reasoner into the original transformer based model for step-by-step reasoning. When system 2 completes multi-step reasoning, its output is regarded as final prediction. Our proposed method achieved the 1st rank on the summing scores across all four DSTC-11 SIMMC 2.1 sub-tasks.</abstract>
<identifier type="citekey">long-etal-2023-improving</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.3</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>15</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning
%A Long, Yuxing
%A Zhang, Huibin
%A Hui, Binyuan
%A Yang, Zhenglu
%A Yuan, Caixia
%A Wang, Xiaojie
%A Huang, Fei
%A Li, Yongbin
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F long-etal-2023-improving
%X To fulfill complex user requirements in a situated conversational scenario, the agent needs to conduct step-by-step multi-modal logic reasoning, which includes locating objects, querying information and searching objects. However, existing methods omit this multi-step procedure and therefore constitutes the risk of shortcuts when making predictions. For example, they may directly copy the information from the dialogue history or simply use the textual description without perform visual reasoning. To address this issue and further boost the system performance, we apply the dual process theory to plug a reasoner into the original transformer based model for step-by-step reasoning. When system 2 completes multi-step reasoning, its output is regarded as final prediction. Our proposed method achieved the 1st rank on the summing scores across all four DSTC-11 SIMMC 2.1 sub-tasks.
%U https://aclanthology.org/2023.dstc-1.3
%P 15-24
Markdown (Informal)
[Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning](https://aclanthology.org/2023.dstc-1.3) (Long et al., DSTC-WS 2023)
ACL
- Yuxing Long, Huibin Zhang, Binyuan Hui, Zhenglu Yang, Caixia Yuan, Xiaojie Wang, Fei Huang, and Yongbin Li. 2023. Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 15–24, Prague, Czech Republic. Association for Computational Linguistics.