<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keim-littman-2022-selecting">
    <titleInfo>
        <title>Selecting Context Clozes for Lightweight Reading Compliance</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Greg</namePart>
        <namePart type="family">Keim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Littman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, Washington</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We explore a novel approach to reading compliance, leveraging large language models to select inline challenges that discourage skipping during reading. This lightweight ‘testing’ is accomplished through automatically identified context clozes where the reader must supply a missing word that would be hard to guess if earlier material was skipped. Clozes are selected by scoring each word by the contrast between its likelihood with and without prior sentences as context, preferring to leave gaps where this contrast is high. We report results of an initial human-participant test that indicates this method can find clozes that have this property.</abstract>
    <identifier type="citekey">keim-littman-2022-selecting</identifier>
    <identifier type="doi">10.18653/v1/2022.bea-1.21</identifier>
    <location>
        <url>https://aclanthology.org/2022.bea-1.21</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>167</start>
            <end>172</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Selecting Context Clozes for Lightweight Reading Compliance
%A Keim, Greg
%A Littman, Michael
%S Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F keim-littman-2022-selecting
%X We explore a novel approach to reading compliance, leveraging large language models to select inline challenges that discourage skipping during reading. This lightweight ‘testing’ is accomplished through automatically identified context clozes where the reader must supply a missing word that would be hard to guess if earlier material was skipped. Clozes are selected by scoring each word by the contrast between its likelihood with and without prior sentences as context, preferring to leave gaps where this contrast is high. We report results of an initial human-participant test that indicates this method can find clozes that have this property.
%R 10.18653/v1/2022.bea-1.21
%U https://aclanthology.org/2022.bea-1.21
%U https://doi.org/10.18653/v1/2022.bea-1.21
%P 167-172

Markdown (Informal)

[Selecting Context Clozes for Lightweight Reading Compliance](https://aclanthology.org/2022.bea-1.21) (Keim & Littman, BEA 2022)

• Selecting Context Clozes for Lightweight Reading Compliance (Keim & Littman, BEA 2022)

ACL

• Greg Keim and Michael Littman. 2022. Selecting Context Clozes for Lightweight Reading Compliance. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 167–172, Seattle, Washington. Association for Computational Linguistics.