@inproceedings{stodden-etal-2023-deplain,
title = "{DE}plain: A {G}erman Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification",
author = "Stodden, Regina and
Momen, Omar and
Kallmeyer, Laura",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.908",
doi = "10.18653/v1/2023.acl-long.908",
pages = "16441--16463",
abstract = "Text simplification is an intralingual translation task in which documents, or sentences of a complex source text are simplified for a target audience. The success of automatic text simplification systems is highly dependent on the quality of parallel data used for training and evaluation. To advance sentence simplification and document simplification in German, this paper presents DEplain, a new dataset of parallel, professionally written and manually aligned simplifications in plain German {``}plain DE{''} or in German: {``}Einfache Sprache{''}. DEplain consists of a news-domain (approx. 500 document pairs, approx. 13k sentence pairs) and a web-domain corpus (approx. 150 aligned documents, approx. 2k aligned sentence pairs). In addition, we are building a web harvester and experimenting with automatic alignment methods to facilitate the integration of non-aligned and to be-published parallel documents. Using this approach, we are dynamically increasing the web-domain corpus, so it is currently extended to approx. 750 document pairs and approx. 3.5k aligned sentence pairs. We show that using DEplain to train a transformer-based seq2seq text simplification model can achieve promising results. We make available the corpus, the adapted alignment methods for German, the web harvester and the trained models here: \url{https://github.com/rstodden/DEPlain}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stodden-etal-2023-deplain">
<titleInfo>
<title>DEplain: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document 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">Omar</namePart>
<namePart type="family">Momen</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>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text simplification is an intralingual translation task in which documents, or sentences of a complex source text are simplified for a target audience. The success of automatic text simplification systems is highly dependent on the quality of parallel data used for training and evaluation. To advance sentence simplification and document simplification in German, this paper presents DEplain, a new dataset of parallel, professionally written and manually aligned simplifications in plain German “plain DE” or in German: “Einfache Sprache”. DEplain consists of a news-domain (approx. 500 document pairs, approx. 13k sentence pairs) and a web-domain corpus (approx. 150 aligned documents, approx. 2k aligned sentence pairs). In addition, we are building a web harvester and experimenting with automatic alignment methods to facilitate the integration of non-aligned and to be-published parallel documents. Using this approach, we are dynamically increasing the web-domain corpus, so it is currently extended to approx. 750 document pairs and approx. 3.5k aligned sentence pairs. We show that using DEplain to train a transformer-based seq2seq text simplification model can achieve promising results. We make available the corpus, the adapted alignment methods for German, the web harvester and the trained models here: https://github.com/rstodden/DEPlain.</abstract>
<identifier type="citekey">stodden-etal-2023-deplain</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.908</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.908</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>16441</start>
<end>16463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DEplain: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification
%A Stodden, Regina
%A Momen, Omar
%A Kallmeyer, Laura
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F stodden-etal-2023-deplain
%X Text simplification is an intralingual translation task in which documents, or sentences of a complex source text are simplified for a target audience. The success of automatic text simplification systems is highly dependent on the quality of parallel data used for training and evaluation. To advance sentence simplification and document simplification in German, this paper presents DEplain, a new dataset of parallel, professionally written and manually aligned simplifications in plain German “plain DE” or in German: “Einfache Sprache”. DEplain consists of a news-domain (approx. 500 document pairs, approx. 13k sentence pairs) and a web-domain corpus (approx. 150 aligned documents, approx. 2k aligned sentence pairs). In addition, we are building a web harvester and experimenting with automatic alignment methods to facilitate the integration of non-aligned and to be-published parallel documents. Using this approach, we are dynamically increasing the web-domain corpus, so it is currently extended to approx. 750 document pairs and approx. 3.5k aligned sentence pairs. We show that using DEplain to train a transformer-based seq2seq text simplification model can achieve promising results. We make available the corpus, the adapted alignment methods for German, the web harvester and the trained models here: https://github.com/rstodden/DEPlain.
%R 10.18653/v1/2023.acl-long.908
%U https://aclanthology.org/2023.acl-long.908
%U https://doi.org/10.18653/v1/2023.acl-long.908
%P 16441-16463
Markdown (Informal)
[DEplain: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification](https://aclanthology.org/2023.acl-long.908) (Stodden et al., ACL 2023)
ACL