@inproceedings{redmiles-etal-2019-comparing,
title = "Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts",
author = "Redmiles, Elissa and
Maszkiewicz, Lisa and
Hwang, Emily and
Kuchhal, Dhruv and
Liu, Everest and
Morales, Miraida and
Peskov, Denis and
Rao, Sudha and
Stevens, Rock and
Gligori\'c, Kristina and
Kross, Sean and
Mazurek, Michelle and
Daum\'e III, Hal",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1489/",
doi = "10.18653/v1/D19-1489",
pages = "4831--4842",
abstract = "The readability of a digital text can influence people's ability to learn new things about a range topics from digital resources (e.g., Wikipedia, WebMD). Readability also impacts search rankings, and is used to evaluate the performance of NLP systems. Despite this, we lack a thorough understanding of how to validly measure readability at scale, especially for domain-specific texts. In this work, we present a comparison of the validity of well-known readability measures and introduce a novel approach, Smart Cloze, which is designed to address shortcomings of existing measures. We compare these approaches across four different corpora: crowdworker-generated stories, Wikipedia articles, security and privacy advice, and health information. On these corpora, we evaluate the convergent and content validity of each measure, and detail tradeoffs in score precision, domain-specificity, and participant burden. These results provide a foundation for more accurate readability measurements and better evaluation of new natural-language-processing systems and tools."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="redmiles-etal-2019-comparing">
<titleInfo>
<title>Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elissa</namePart>
<namePart type="family">Redmiles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Maszkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Kuchhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Everest</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miraida</namePart>
<namePart type="family">Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Peskov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudha</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rock</namePart>
<namePart type="family">Stevens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Gligorić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Kross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Mazurek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hal</namePart>
<namePart type="family">Daumé III</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The readability of a digital text can influence people’s ability to learn new things about a range topics from digital resources (e.g., Wikipedia, WebMD). Readability also impacts search rankings, and is used to evaluate the performance of NLP systems. Despite this, we lack a thorough understanding of how to validly measure readability at scale, especially for domain-specific texts. In this work, we present a comparison of the validity of well-known readability measures and introduce a novel approach, Smart Cloze, which is designed to address shortcomings of existing measures. We compare these approaches across four different corpora: crowdworker-generated stories, Wikipedia articles, security and privacy advice, and health information. On these corpora, we evaluate the convergent and content validity of each measure, and detail tradeoffs in score precision, domain-specificity, and participant burden. These results provide a foundation for more accurate readability measurements and better evaluation of new natural-language-processing systems and tools.</abstract>
<identifier type="citekey">redmiles-etal-2019-comparing</identifier>
<identifier type="doi">10.18653/v1/D19-1489</identifier>
<location>
<url>https://aclanthology.org/D19-1489/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4831</start>
<end>4842</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
%A Redmiles, Elissa
%A Maszkiewicz, Lisa
%A Hwang, Emily
%A Kuchhal, Dhruv
%A Liu, Everest
%A Morales, Miraida
%A Peskov, Denis
%A Rao, Sudha
%A Stevens, Rock
%A Gligorić, Kristina
%A Kross, Sean
%A Mazurek, Michelle
%A Daumé III, Hal
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F redmiles-etal-2019-comparing
%X The readability of a digital text can influence people’s ability to learn new things about a range topics from digital resources (e.g., Wikipedia, WebMD). Readability also impacts search rankings, and is used to evaluate the performance of NLP systems. Despite this, we lack a thorough understanding of how to validly measure readability at scale, especially for domain-specific texts. In this work, we present a comparison of the validity of well-known readability measures and introduce a novel approach, Smart Cloze, which is designed to address shortcomings of existing measures. We compare these approaches across four different corpora: crowdworker-generated stories, Wikipedia articles, security and privacy advice, and health information. On these corpora, we evaluate the convergent and content validity of each measure, and detail tradeoffs in score precision, domain-specificity, and participant burden. These results provide a foundation for more accurate readability measurements and better evaluation of new natural-language-processing systems and tools.
%R 10.18653/v1/D19-1489
%U https://aclanthology.org/D19-1489/
%U https://doi.org/10.18653/v1/D19-1489
%P 4831-4842
Markdown (Informal)
[Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts](https://aclanthology.org/D19-1489/) (Redmiles et al., EMNLP-IJCNLP 2019)
ACL
- Elissa Redmiles, Lisa Maszkiewicz, Emily Hwang, Dhruv Kuchhal, Everest Liu, Miraida Morales, Denis Peskov, Sudha Rao, Rock Stevens, Kristina Gligorić, Sean Kross, Michelle Mazurek, and Hal Daumé III. 2019. Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4831–4842, Hong Kong, China. Association for Computational Linguistics.