@inproceedings{stodden-kallmeyer-2020-multi,
title = "A multi-lingual and cross-domain analysis of features for text simplification",
author = "Stodden, Regina and
Kallmeyer, Laura",
editor = "Gala, N{\'u}ria and
Wilkens, Rodrigo",
booktitle = "Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.readi-1.12",
pages = "77--84",
abstract = "In text simplification and readability research, several features have been proposed to estimate or simplify a complex text, e.g., readability scores, sentence length, or proportion of POS tags. These features are however mainly developed for English. In this paper, we investigate their relevance for Czech, German, English, Spanish, and Italian text simplification corpora. Our multi-lingual and multi-domain corpus analysis shows that the relevance of different features for text simplification is different per corpora, language, and domain. For example, the relevance of the lexical complexity is different across all languages, the BLEU score across all domains, and 14 features within the web domain corpora. Overall, the negative statistical tests regarding the other features across and within domains and languages lead to the assumption that text simplification models may be transferable between different domains or different languages.",
language = "English",
ISBN = "979-10-95546-45-0",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stodden-kallmeyer-2020-multi">
<titleInfo>
<title>A multi-lingual and cross-domain analysis of features for text simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Kallmeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Gala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-45-0</identifier>
</relatedItem>
<abstract>In text simplification and readability research, several features have been proposed to estimate or simplify a complex text, e.g., readability scores, sentence length, or proportion of POS tags. These features are however mainly developed for English. In this paper, we investigate their relevance for Czech, German, English, Spanish, and Italian text simplification corpora. Our multi-lingual and multi-domain corpus analysis shows that the relevance of different features for text simplification is different per corpora, language, and domain. For example, the relevance of the lexical complexity is different across all languages, the BLEU score across all domains, and 14 features within the web domain corpora. Overall, the negative statistical tests regarding the other features across and within domains and languages lead to the assumption that text simplification models may be transferable between different domains or different languages.</abstract>
<identifier type="citekey">stodden-kallmeyer-2020-multi</identifier>
<location>
<url>https://aclanthology.org/2020.readi-1.12</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>77</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A multi-lingual and cross-domain analysis of features for text simplification
%A Stodden, Regina
%A Kallmeyer, Laura
%Y Gala, Núria
%Y Wilkens, Rodrigo
%S Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-45-0
%G English
%F stodden-kallmeyer-2020-multi
%X In text simplification and readability research, several features have been proposed to estimate or simplify a complex text, e.g., readability scores, sentence length, or proportion of POS tags. These features are however mainly developed for English. In this paper, we investigate their relevance for Czech, German, English, Spanish, and Italian text simplification corpora. Our multi-lingual and multi-domain corpus analysis shows that the relevance of different features for text simplification is different per corpora, language, and domain. For example, the relevance of the lexical complexity is different across all languages, the BLEU score across all domains, and 14 features within the web domain corpora. Overall, the negative statistical tests regarding the other features across and within domains and languages lead to the assumption that text simplification models may be transferable between different domains or different languages.
%U https://aclanthology.org/2020.readi-1.12
%P 77-84
Markdown (Informal)
[A multi-lingual and cross-domain analysis of features for text simplification](https://aclanthology.org/2020.readi-1.12) (Stodden & Kallmeyer, READI 2020)
ACL