@inproceedings{anschutz-etal-2023-language,
title = "Language Models for {G}erman Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training",
author = {Ansch{\"u}tz, Miriam and
Oehms, Joshua and
Wimmer, Thomas and
Jezierski, Bart{\l}omiej and
Groh, Georg},
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.74",
doi = "10.18653/v1/2023.findings-acl.74",
pages = "1147--1158",
abstract = "Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anschutz-etal-2023-language">
<titleInfo>
<title>Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Anschütz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Oehms</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wimmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartłomiej</namePart>
<namePart type="family">Jezierski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Groh</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.</abstract>
<identifier type="citekey">anschutz-etal-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.74</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.74</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1147</start>
<end>1158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training
%A Anschütz, Miriam
%A Oehms, Joshua
%A Wimmer, Thomas
%A Jezierski, Bartłomiej
%A Groh, Georg
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F anschutz-etal-2023-language
%X Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.
%R 10.18653/v1/2023.findings-acl.74
%U https://aclanthology.org/2023.findings-acl.74
%U https://doi.org/10.18653/v1/2023.findings-acl.74
%P 1147-1158
Markdown (Informal)
[Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training](https://aclanthology.org/2023.findings-acl.74) (Anschütz et al., Findings 2023)
ACL