<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thayaparan-etal-2022-diff">
    <titleInfo>
        <title>Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mokanarangan</namePart>
        <namePart type="family">Thayaparan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Valentino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deborah</namePart>
        <namePart type="family">Ferreira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julia</namePart>
        <namePart type="family">Rozanova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">André</namePart>
        <namePart type="family">Freitas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>This paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization. Specifically, Diff- Explainer allows for the fine-tuning of neural representations within a constrained optimization framework to answer and explain multi-hop questions in natural language. To demonstrate the efficacy of the hybrid framework, we combine existing ILP-based solvers for multi-hop Question Answering (QA) with Transformer-based representations. An extensive empirical evaluation on scientific and commonsense QA tasks demonstrates that the integration of explicit constraints in a end-to-end differentiable framework can significantly improve the performance of non- differentiable ILP solvers (8.91%–13.3%). Moreover, additional analysis reveals that Diff-Explainer is able to achieve strong performance when compared to standalone Transformers and previous multi-hop approaches while still providing structured explanations in support of its predictions.</abstract>
    <identifier type="citekey">thayaparan-etal-2022-diff</identifier>
    <identifier type="doi">10.1162/tacl_a_00508</identifier>
    <location>
        <url>https://aclanthology.org/2022.tacl-1.64</url>
    </location>
    <part>
        <date>2022</date>
        <detail type="volume"><number>10</number></detail>
        <extent unit="page">
            <start>1103</start>
            <end>1119</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
%A Thayaparan, Mokanarangan
%A Valentino, Marco
%A Ferreira, Deborah
%A Rozanova, Julia
%A Freitas, André
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F thayaparan-etal-2022-diff
%X This paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization. Specifically, Diff- Explainer allows for the fine-tuning of neural representations within a constrained optimization framework to answer and explain multi-hop questions in natural language. To demonstrate the efficacy of the hybrid framework, we combine existing ILP-based solvers for multi-hop Question Answering (QA) with Transformer-based representations. An extensive empirical evaluation on scientific and commonsense QA tasks demonstrates that the integration of explicit constraints in a end-to-end differentiable framework can significantly improve the performance of non- differentiable ILP solvers (8.91%–13.3%). Moreover, additional analysis reveals that Diff-Explainer is able to achieve strong performance when compared to standalone Transformers and previous multi-hop approaches while still providing structured explanations in support of its predictions.
%R 10.1162/tacl_a_00508
%U https://aclanthology.org/2022.tacl-1.64
%U https://doi.org/10.1162/tacl_a_00508
%P 1103-1119

Markdown (Informal)

[Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference](https://aclanthology.org/2022.tacl-1.64) (Thayaparan et al., TACL 2022)

• Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference (Thayaparan et al., TACL 2022)

ACL

• Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, and André Freitas. 2022. Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference. Transactions of the Association for Computational Linguistics, 10:1103–1119.