@inproceedings{hamster-2022-everybody,
title = "Everybody likes short sentences - A Data Analysis for the Text Complexity {DE} Challenge 2022",
author = "Hamster, Ulf A.",
editor = {M{\"o}ller, Sebastian and
Mohtaj, Salar and
Naderi, Babak},
booktitle = "Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text",
month = sep,
year = "2022",
address = "Potsdam, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.germeval-1.2",
pages = "10--14",
abstract = "The German Text Complexity Assessment Shared Task in KONVENS 2022 explores how to predict a complexity score for sentence examples from language learners{'} perspective. Our modeling approach for this shared task utilizes off-the-shelf NLP tools for feature engineering and a Random Forest regression model. We identified the text length, or resp. the logarithm of a sentence{'}s string length, as the most important feature to predict the complexity score. Further analysis showed that the Pearson correlation between text length and complexity score is about $\rho$ {\mbox{$\approx$}} 0.777. A sensitivity analysis on the loss function revealed that semantic SBert features impact the complexity score as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamster-2022-everybody">
<titleInfo>
<title>Everybody likes short sentences - A Data Analysis for the Text Complexity DE Challenge 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulf</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Hamster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salar</namePart>
<namePart type="family">Mohtaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Babak</namePart>
<namePart type="family">Naderi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Potsdam, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The German Text Complexity Assessment Shared Task in KONVENS 2022 explores how to predict a complexity score for sentence examples from language learners’ perspective. Our modeling approach for this shared task utilizes off-the-shelf NLP tools for feature engineering and a Random Forest regression model. We identified the text length, or resp. the logarithm of a sentence’s string length, as the most important feature to predict the complexity score. Further analysis showed that the Pearson correlation between text length and complexity score is about ρ \approx 0.777. A sensitivity analysis on the loss function revealed that semantic SBert features impact the complexity score as well.</abstract>
<identifier type="citekey">hamster-2022-everybody</identifier>
<location>
<url>https://aclanthology.org/2022.germeval-1.2</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>10</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Everybody likes short sentences - A Data Analysis for the Text Complexity DE Challenge 2022
%A Hamster, Ulf A.
%Y Möller, Sebastian
%Y Mohtaj, Salar
%Y Naderi, Babak
%S Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text
%D 2022
%8 September
%I Association for Computational Linguistics
%C Potsdam, Germany
%F hamster-2022-everybody
%X The German Text Complexity Assessment Shared Task in KONVENS 2022 explores how to predict a complexity score for sentence examples from language learners’ perspective. Our modeling approach for this shared task utilizes off-the-shelf NLP tools for feature engineering and a Random Forest regression model. We identified the text length, or resp. the logarithm of a sentence’s string length, as the most important feature to predict the complexity score. Further analysis showed that the Pearson correlation between text length and complexity score is about ρ \approx 0.777. A sensitivity analysis on the loss function revealed that semantic SBert features impact the complexity score as well.
%U https://aclanthology.org/2022.germeval-1.2
%P 10-14
Markdown (Informal)
[Everybody likes short sentences - A Data Analysis for the Text Complexity DE Challenge 2022](https://aclanthology.org/2022.germeval-1.2) (Hamster, GermEval 2022)
ACL