@inproceedings{chatzipanagiotidis-etal-2021-broad,
title = "Broad Linguistic Complexity Analysis for {G}reek Readability Classification",
author = "Chatzipanagiotidis, Savvas and
Giagkou, Maria and
Meurers, Detmar",
editor = "Burstein, Jill and
Horbach, Andrea and
Kochmar, Ekaterina and
Laarmann-Quante, Ronja and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bea-1.5/",
pages = "48--58",
abstract = "This paper explores the linguistic complexity of Greek textbooks as a readability classification task. We analyze textbook corpora for different school subjects and textbooks for Greek as a Second Language, covering a very wide spectrum of school age groups and proficiency levels. A broad range of quantifiable linguistic complexity features (lexical, morphological and syntactic) are extracted and calculated. Conducting experiments with different feature subsets, we show that the different linguistic dimensions contribute orthogonal information, each contributing towards the highest result achieved using all linguistic feature subsets. A readability classifier trained on this basis reaches a classification accuracy of 88.16{\%} for the Greek as a Second Language corpus. To investigate the generalizability of the classification models, we also perform cross-corpus evaluations. We show that the model trained on the most varied text collection (for Greek as a school subject) generalizes best. In addition to advancing the state of the art for Greek readability analysis, the paper also contributes insights on the role of different feature sets and training setups for generalizable readability classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatzipanagiotidis-etal-2021-broad">
<titleInfo>
<title>Broad Linguistic Complexity Analysis for Greek Readability Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Savvas</namePart>
<namePart type="family">Chatzipanagiotidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Giagkou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Detmar</namePart>
<namePart type="family">Meurers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the linguistic complexity of Greek textbooks as a readability classification task. We analyze textbook corpora for different school subjects and textbooks for Greek as a Second Language, covering a very wide spectrum of school age groups and proficiency levels. A broad range of quantifiable linguistic complexity features (lexical, morphological and syntactic) are extracted and calculated. Conducting experiments with different feature subsets, we show that the different linguistic dimensions contribute orthogonal information, each contributing towards the highest result achieved using all linguistic feature subsets. A readability classifier trained on this basis reaches a classification accuracy of 88.16% for the Greek as a Second Language corpus. To investigate the generalizability of the classification models, we also perform cross-corpus evaluations. We show that the model trained on the most varied text collection (for Greek as a school subject) generalizes best. In addition to advancing the state of the art for Greek readability analysis, the paper also contributes insights on the role of different feature sets and training setups for generalizable readability classification.</abstract>
<identifier type="citekey">chatzipanagiotidis-etal-2021-broad</identifier>
<location>
<url>https://aclanthology.org/2021.bea-1.5/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>48</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Broad Linguistic Complexity Analysis for Greek Readability Classification
%A Chatzipanagiotidis, Savvas
%A Giagkou, Maria
%A Meurers, Detmar
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Kochmar, Ekaterina
%Y Laarmann-Quante, Ronja
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F chatzipanagiotidis-etal-2021-broad
%X This paper explores the linguistic complexity of Greek textbooks as a readability classification task. We analyze textbook corpora for different school subjects and textbooks for Greek as a Second Language, covering a very wide spectrum of school age groups and proficiency levels. A broad range of quantifiable linguistic complexity features (lexical, morphological and syntactic) are extracted and calculated. Conducting experiments with different feature subsets, we show that the different linguistic dimensions contribute orthogonal information, each contributing towards the highest result achieved using all linguistic feature subsets. A readability classifier trained on this basis reaches a classification accuracy of 88.16% for the Greek as a Second Language corpus. To investigate the generalizability of the classification models, we also perform cross-corpus evaluations. We show that the model trained on the most varied text collection (for Greek as a school subject) generalizes best. In addition to advancing the state of the art for Greek readability analysis, the paper also contributes insights on the role of different feature sets and training setups for generalizable readability classification.
%U https://aclanthology.org/2021.bea-1.5/
%P 48-58
Markdown (Informal)
[Broad Linguistic Complexity Analysis for Greek Readability Classification](https://aclanthology.org/2021.bea-1.5/) (Chatzipanagiotidis et al., BEA 2021)
ACL