@inproceedings{attia-etal-2023-statistical,
title = "Statistical Measures for Readability Assessment",
author = "Attia, Mohammed and
Samih, Younes and
Ehara, Yo",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Pirinen, Flammie and
Alnajjar, Khalid and
Miyagawa, So and
Bizzoni, Yuri and
Partanen, Niko and
Rueter, Jack},
booktitle = "Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages",
month = dec,
year = "2023",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlp4dh-1.19",
pages = "153--161",
abstract = "Neural models and deep learning techniques have predominantly been used in many tasks of natural language processing (NLP), including automatic readability assessment (ARA). They apply deep transfer learning and enjoy high accuracy. However, most of the models still cannot leverage long dependence such as inter-sentential topic-level or document-level information because of their structure and computational cost. Moreover, neural models usually have low interpretability. In this paper, we propose a generalization of passage-level, corpus-level, document-level and topic-level features. In our experiments, we show the effectiveness of {``}Statistical Lexical Spread (SLS){''} features when combined with IDF (inverse document frequency) and TF-IDF (term frequency{--}inverse document frequency), which adds a topological perspective (inter-document) to readability to complement the typological approaches (intra-document) used in traditional readability formulas. Interestingly, simply adding these features in BERT models outperformed state-of-the-art systems trained on a large number of hand-crafted features derived from heavy linguistic processing. In analysis, we show that SLS is also easy-to-interpret because SLS computes lexical features, which appear explicitly in texts, compared to parameters in neural models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="attia-etal-2023-statistical">
<titleInfo>
<title>Statistical Measures for Readability Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Attia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yo</namePart>
<namePart type="family">Ehara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural models and deep learning techniques have predominantly been used in many tasks of natural language processing (NLP), including automatic readability assessment (ARA). They apply deep transfer learning and enjoy high accuracy. However, most of the models still cannot leverage long dependence such as inter-sentential topic-level or document-level information because of their structure and computational cost. Moreover, neural models usually have low interpretability. In this paper, we propose a generalization of passage-level, corpus-level, document-level and topic-level features. In our experiments, we show the effectiveness of “Statistical Lexical Spread (SLS)” features when combined with IDF (inverse document frequency) and TF-IDF (term frequency–inverse document frequency), which adds a topological perspective (inter-document) to readability to complement the typological approaches (intra-document) used in traditional readability formulas. Interestingly, simply adding these features in BERT models outperformed state-of-the-art systems trained on a large number of hand-crafted features derived from heavy linguistic processing. In analysis, we show that SLS is also easy-to-interpret because SLS computes lexical features, which appear explicitly in texts, compared to parameters in neural models.</abstract>
<identifier type="citekey">attia-etal-2023-statistical</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4dh-1.19</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>153</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Measures for Readability Assessment
%A Attia, Mohammed
%A Samih, Younes
%A Ehara, Yo
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Pirinen, Flammie
%Y Alnajjar, Khalid
%Y Miyagawa, So
%Y Bizzoni, Yuri
%Y Partanen, Niko
%Y Rueter, Jack
%S Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages
%D 2023
%8 December
%I Association for Computational Linguistics
%C Tokyo, Japan
%F attia-etal-2023-statistical
%X Neural models and deep learning techniques have predominantly been used in many tasks of natural language processing (NLP), including automatic readability assessment (ARA). They apply deep transfer learning and enjoy high accuracy. However, most of the models still cannot leverage long dependence such as inter-sentential topic-level or document-level information because of their structure and computational cost. Moreover, neural models usually have low interpretability. In this paper, we propose a generalization of passage-level, corpus-level, document-level and topic-level features. In our experiments, we show the effectiveness of “Statistical Lexical Spread (SLS)” features when combined with IDF (inverse document frequency) and TF-IDF (term frequency–inverse document frequency), which adds a topological perspective (inter-document) to readability to complement the typological approaches (intra-document) used in traditional readability formulas. Interestingly, simply adding these features in BERT models outperformed state-of-the-art systems trained on a large number of hand-crafted features derived from heavy linguistic processing. In analysis, we show that SLS is also easy-to-interpret because SLS computes lexical features, which appear explicitly in texts, compared to parameters in neural models.
%U https://aclanthology.org/2023.nlp4dh-1.19
%P 153-161
Markdown (Informal)
[Statistical Measures for Readability Assessment](https://aclanthology.org/2023.nlp4dh-1.19) (Attia et al., NLP4DH-IWCLUL 2023)
ACL
- Mohammed Attia, Younes Samih, and Yo Ehara. 2023. Statistical Measures for Readability Assessment. In Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages, pages 153–161, Tokyo, Japan. Association for Computational Linguistics.