@inproceedings{li-etal-2023-art,
title = "{ART}: rule b{A}sed futu{R}e-inference deduc{T}ion",
author = "Li, Mengze and
Zhao, Tianqi and
Jionghao, Bai and
He, Baoyi and
Miao, Jiaxu and
Ji, Wei and
Lv, Zheqi and
Zhao, Zhou and
Zhang, Shengyu and
Zhang, Wenqiao and
Wu, Fei",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.592",
doi = "10.18653/v1/2023.emnlp-main.592",
pages = "9512--9522",
abstract = "Deductive reasoning is a crucial cognitive ability of humanity, allowing us to derive valid conclusions from premises and observations. However, existing works mainly focus on language-based premises and generally neglect deductive reasoning from visual observations. In this work, we introduce rule bAsed futuRe-inference deducTion (ART), which aims at deducing the correct future event based on the visual phenomenon (a video) and the rule-based premises, along with an explanation of the reasoning process. To advance this field, we construct a large-scale densely annotated dataset (Video-ART), where the premises, future event candidates, the reasoning process explanation, and auxiliary commonsense knowledge (e.g., actions and appearance) are annotated by annotators. Upon Video-ART, we develop a strong baseline named ARTNet. In essence, guided by commonsense knowledge, ARTNet learns to identify the target video character and perceives its visual clues related to the future event. Then, ARTNet rigorously applies the given premises to conduct reasoning from the identified information to future events, through a non-parametric rule reasoning network and a reasoning-path review module. Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations and the effectiveness over existing works.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-art">
<titleInfo>
<title>ART: rule bAsed futuRe-inference deducTion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianqi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bai</namePart>
<namePart type="family">Jionghao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoyi</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxu</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheqi</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deductive reasoning is a crucial cognitive ability of humanity, allowing us to derive valid conclusions from premises and observations. However, existing works mainly focus on language-based premises and generally neglect deductive reasoning from visual observations. In this work, we introduce rule bAsed futuRe-inference deducTion (ART), which aims at deducing the correct future event based on the visual phenomenon (a video) and the rule-based premises, along with an explanation of the reasoning process. To advance this field, we construct a large-scale densely annotated dataset (Video-ART), where the premises, future event candidates, the reasoning process explanation, and auxiliary commonsense knowledge (e.g., actions and appearance) are annotated by annotators. Upon Video-ART, we develop a strong baseline named ARTNet. In essence, guided by commonsense knowledge, ARTNet learns to identify the target video character and perceives its visual clues related to the future event. Then, ARTNet rigorously applies the given premises to conduct reasoning from the identified information to future events, through a non-parametric rule reasoning network and a reasoning-path review module. Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations and the effectiveness over existing works.</abstract>
<identifier type="citekey">li-etal-2023-art</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.592</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.592</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9512</start>
<end>9522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ART: rule bAsed futuRe-inference deducTion
%A Li, Mengze
%A Zhao, Tianqi
%A Jionghao, Bai
%A He, Baoyi
%A Miao, Jiaxu
%A Ji, Wei
%A Lv, Zheqi
%A Zhao, Zhou
%A Zhang, Shengyu
%A Zhang, Wenqiao
%A Wu, Fei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-art
%X Deductive reasoning is a crucial cognitive ability of humanity, allowing us to derive valid conclusions from premises and observations. However, existing works mainly focus on language-based premises and generally neglect deductive reasoning from visual observations. In this work, we introduce rule bAsed futuRe-inference deducTion (ART), which aims at deducing the correct future event based on the visual phenomenon (a video) and the rule-based premises, along with an explanation of the reasoning process. To advance this field, we construct a large-scale densely annotated dataset (Video-ART), where the premises, future event candidates, the reasoning process explanation, and auxiliary commonsense knowledge (e.g., actions and appearance) are annotated by annotators. Upon Video-ART, we develop a strong baseline named ARTNet. In essence, guided by commonsense knowledge, ARTNet learns to identify the target video character and perceives its visual clues related to the future event. Then, ARTNet rigorously applies the given premises to conduct reasoning from the identified information to future events, through a non-parametric rule reasoning network and a reasoning-path review module. Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations and the effectiveness over existing works.
%R 10.18653/v1/2023.emnlp-main.592
%U https://aclanthology.org/2023.emnlp-main.592
%U https://doi.org/10.18653/v1/2023.emnlp-main.592
%P 9512-9522
Markdown (Informal)
[ART: rule bAsed futuRe-inference deducTion](https://aclanthology.org/2023.emnlp-main.592) (Li et al., EMNLP 2023)
ACL
- Mengze Li, Tianqi Zhao, Bai Jionghao, Baoyi He, Jiaxu Miao, Wei Ji, Zheqi Lv, Zhou Zhao, Shengyu Zhang, Wenqiao Zhang, and Fei Wu. 2023. ART: rule bAsed futuRe-inference deducTion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9512–9522, Singapore. Association for Computational Linguistics.