<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lertvittayakumjorn-toni-2021-explanation">
    <titleInfo>
        <title>Explanation-Based Human Debugging of NLP Models: A Survey</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Piyawat</namePart>
        <namePart type="family">Lertvittayakumjorn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Francesca</namePart>
        <namePart type="family">Toni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre>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>academic journal</genre>
    </relatedItem>
    <abstract>Abstract Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components affect the feedback providers, and highlight open problems that could be future research directions.</abstract>
    <identifier type="citekey">lertvittayakumjorn-toni-2021-explanation</identifier>
    <identifier type="doi">10.1162/tacl_a_00440</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.90</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>1508</start>
            <end>1528</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Explanation-Based Human Debugging of NLP Models: A Survey
%A Lertvittayakumjorn, Piyawat
%A Toni, Francesca
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F lertvittayakumjorn-toni-2021-explanation
%X Abstract Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components affect the feedback providers, and highlight open problems that could be future research directions.
%9 journal article
%R 10.1162/tacl_a_00440
%U https://aclanthology.org/2021.tacl-1.90
%U https://doi.org/10.1162/tacl_a_00440
%P 1508-1528

Markdown (Informal)

[Explanation-Based Human Debugging of NLP Models: A Survey](https://aclanthology.org/2021.tacl-1.90) (Lertvittayakumjorn & Toni, TACL 2021)

• Explanation-Based Human Debugging of NLP Models: A Survey (Lertvittayakumjorn & Toni, TACL 2021)

ACL

• Piyawat Lertvittayakumjorn and Francesca Toni. 2021. Explanation-Based Human Debugging of NLP Models: A Survey. Transactions of the Association for Computational Linguistics, 9:1508–1528.