<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2018-entity">
    <titleInfo>
        <title>Entity Tracking Improves Cloze-style Reading Comprehension</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Luong</namePart>
        <namePart type="family">Hoang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sam</namePart>
        <namePart type="family">Wiseman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Rush</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct&quot;-&quot;nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent work has improved on modeling for reading comprehension tasks with simple approaches such as the Attention Sum-Reader; however, automatic systems still significantly trail human performance. Analysis suggests that many of the remaining hard instances are related to the inability to track entity-references throughout documents. This work focuses on these hard entity tracking cases with two extensions: (1) additional entity features, and (2) training with a multi-task tracking objective. We show that these simple modifications improve performance both independently and in combination, and we outperform the previous state of the art on the LAMBADA dataset by 8 pts, particularly on difficult entity examples. We also effectively match the performance of more complicated models on the named entity portion of the CBT dataset.</abstract>
    <identifier type="citekey">hoang-etal-2018-entity</identifier>
    <identifier type="doi">10.18653/v1/D18-1130</identifier>
    <location>
        <url>https://aclanthology.org/D18-1130</url>
    </location>
    <part>
        <date>2018-oct&quot;-&quot;nov</date>
        <extent unit="page">
            <start>1049</start>
            <end>1055</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Entity Tracking Improves Cloze-style Reading Comprehension
%A Hoang, Luong
%A Wiseman, Sam
%A Rush, Alexander
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F hoang-etal-2018-entity
%X Recent work has improved on modeling for reading comprehension tasks with simple approaches such as the Attention Sum-Reader; however, automatic systems still significantly trail human performance. Analysis suggests that many of the remaining hard instances are related to the inability to track entity-references throughout documents. This work focuses on these hard entity tracking cases with two extensions: (1) additional entity features, and (2) training with a multi-task tracking objective. We show that these simple modifications improve performance both independently and in combination, and we outperform the previous state of the art on the LAMBADA dataset by 8 pts, particularly on difficult entity examples. We also effectively match the performance of more complicated models on the named entity portion of the CBT dataset.
%R 10.18653/v1/D18-1130
%U https://aclanthology.org/D18-1130
%U https://doi.org/10.18653/v1/D18-1130
%P 1049-1055

Markdown (Informal)

[Entity Tracking Improves Cloze-style Reading Comprehension](https://aclanthology.org/D18-1130) (Hoang et al., EMNLP 2018)

• Entity Tracking Improves Cloze-style Reading Comprehension (Hoang et al., EMNLP 2018)

ACL

• Luong Hoang, Sam Wiseman, and Alexander Rush. 2018. Entity Tracking Improves Cloze-style Reading Comprehension. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1049–1055, Brussels, Belgium. Association for Computational Linguistics.