<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tuan-etal-2023-causaldialogue">
    <titleInfo>
        <title>CausalDialogue: Modeling Utterance-level Causality in Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yi-Lin</namePart>
        <namePart type="family">Tuan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alon</namePart>
        <namePart type="family">Albalak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenda</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Saxon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Connor</namePart>
        <namePart type="family">Pryor</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lise</namePart>
        <namePart type="family">Getoor</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="given">Yang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the needs of considering causality in dialogue generation, we built a comprehensive benchmark on CausalDialogue dataset using different models, inference, and training methods. Through experiments, we find that a causality-inspired loss like ExMATE can improve the diversity and agility of conventional loss function and there is still room for improvement to reach human-level quality on this new dataset.</abstract>
    <identifier type="citekey">tuan-etal-2023-causaldialogue</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.792</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.792</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>12506</start>
            <end>12522</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CausalDialogue: Modeling Utterance-level Causality in Conversations
%A Tuan, Yi-Lin
%A Albalak, Alon
%A Xu, Wenda
%A Saxon, Michael
%A Pryor, Connor
%A Getoor, Lise
%A Wang, William Yang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tuan-etal-2023-causaldialogue
%X Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the needs of considering causality in dialogue generation, we built a comprehensive benchmark on CausalDialogue dataset using different models, inference, and training methods. Through experiments, we find that a causality-inspired loss like ExMATE can improve the diversity and agility of conventional loss function and there is still room for improvement to reach human-level quality on this new dataset.
%R 10.18653/v1/2023.findings-acl.792
%U https://aclanthology.org/2023.findings-acl.792
%U https://doi.org/10.18653/v1/2023.findings-acl.792
%P 12506-12522

Markdown (Informal)

[CausalDialogue: Modeling Utterance-level Causality in Conversations](https://aclanthology.org/2023.findings-acl.792) (Tuan et al., Findings 2023)

• CausalDialogue: Modeling Utterance-level Causality in Conversations (Tuan et al., Findings 2023)

ACL

• Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor Pryor, Lise Getoor, and William Yang Wang. 2023. CausalDialogue: Modeling Utterance-level Causality in Conversations. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12506–12522, Toronto, Canada. Association for Computational Linguistics.