<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hua-zhang-2022-system">
    <titleInfo>
        <title>System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenyue</namePart>
        <namePart type="family">Hua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongfeng</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</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">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Logical reasoning is a challenge for many current NLP neural network models since it requires more than the ability of learning informative representations from data. Inspired by the Dual Process Theory in cognitive science — which proposes that human cognition process involves two stages: an intuitive, unconscious and fast process relying on perception calledSystem 1, and a logical, conscious and slow process performing complex reasoning called System 2 — we leverage neural logic reasoning (System 2) on top of the representation learning models (System 1), which conducts explicit neural-based differentiable logical reasoning on top of the representations learned by the base neural models. Based on experiments on the commonsense knowledge graph completion task, we show that the two-system architecture always improves from its System 1 model alone. Experiments also show that both the rule-driven logical regularizer and the data-driven value regularizer are important and the performance improvement is marginal without the two regularizers, which indicates that learning from both logical prior and training data is important for reasoning tasks.</abstract>
    <identifier type="citekey">hua-zhang-2022-system</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.42</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.42</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>601</start>
            <end>612</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning
%A Hua, Wenyue
%A Zhang, Yongfeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hua-zhang-2022-system
%X Logical reasoning is a challenge for many current NLP neural network models since it requires more than the ability of learning informative representations from data. Inspired by the Dual Process Theory in cognitive science — which proposes that human cognition process involves two stages: an intuitive, unconscious and fast process relying on perception calledSystem 1, and a logical, conscious and slow process performing complex reasoning called System 2 — we leverage neural logic reasoning (System 2) on top of the representation learning models (System 1), which conducts explicit neural-based differentiable logical reasoning on top of the representations learned by the base neural models. Based on experiments on the commonsense knowledge graph completion task, we show that the two-system architecture always improves from its System 1 model alone. Experiments also show that both the rule-driven logical regularizer and the data-driven value regularizer are important and the performance improvement is marginal without the two regularizers, which indicates that learning from both logical prior and training data is important for reasoning tasks.
%R 10.18653/v1/2022.findings-emnlp.42
%U https://aclanthology.org/2022.findings-emnlp.42
%U https://doi.org/10.18653/v1/2022.findings-emnlp.42
%P 601-612

Markdown (Informal)

[System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning](https://aclanthology.org/2022.findings-emnlp.42) (Hua & Zhang, Findings 2022)

• System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning (Hua & Zhang, Findings 2022)

ACL

• Wenyue Hua and Yongfeng Zhang. 2022. System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 601–612, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.