@inproceedings{vlantis-etal-2024-benchmarking,
title = "Benchmarking the Simplification of {D}utch Municipal Text",
author = "Vlantis, Daniel and
Gornishka, Iva and
Wang, Shuai",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.199",
pages = "2217--2226",
abstract = "Text simplification (TS) makes written information more accessible to all people, especially those with cognitive or language impairments. Despite much progress in TS due to advances in NLP technology, the bottleneck issue of lack of data for low-resource languages persists. Dutch is one of these languages that lack a monolingual simplification corpus. In this paper, we use English as a pivot language for the simplification of Dutch medical and municipal text. We experiment with augmenting training data and corpus choice for this pivot-based approach. We compare the results to a baseline and an end-to-end LLM approach using the GPT 3.5 Turbo model. Our evaluation shows that, while we can substantially improve the results of the pivot pipeline, the zero-shot end-to-end GPT-based simplification performs better on all metrics. Our work shows how an existing pivot-based pipeline can be improved for simplifying Dutch medical text. Moreover, we provide baselines for the comparison in the domain of Dutch municipal text and make our corresponding evaluation dataset publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vlantis-etal-2024-benchmarking">
<titleInfo>
<title>Benchmarking the Simplification of Dutch Municipal Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Vlantis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iva</namePart>
<namePart type="family">Gornishka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text simplification (TS) makes written information more accessible to all people, especially those with cognitive or language impairments. Despite much progress in TS due to advances in NLP technology, the bottleneck issue of lack of data for low-resource languages persists. Dutch is one of these languages that lack a monolingual simplification corpus. In this paper, we use English as a pivot language for the simplification of Dutch medical and municipal text. We experiment with augmenting training data and corpus choice for this pivot-based approach. We compare the results to a baseline and an end-to-end LLM approach using the GPT 3.5 Turbo model. Our evaluation shows that, while we can substantially improve the results of the pivot pipeline, the zero-shot end-to-end GPT-based simplification performs better on all metrics. Our work shows how an existing pivot-based pipeline can be improved for simplifying Dutch medical text. Moreover, we provide baselines for the comparison in the domain of Dutch municipal text and make our corresponding evaluation dataset publicly available.</abstract>
<identifier type="citekey">vlantis-etal-2024-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.199</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2217</start>
<end>2226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking the Simplification of Dutch Municipal Text
%A Vlantis, Daniel
%A Gornishka, Iva
%A Wang, Shuai
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F vlantis-etal-2024-benchmarking
%X Text simplification (TS) makes written information more accessible to all people, especially those with cognitive or language impairments. Despite much progress in TS due to advances in NLP technology, the bottleneck issue of lack of data for low-resource languages persists. Dutch is one of these languages that lack a monolingual simplification corpus. In this paper, we use English as a pivot language for the simplification of Dutch medical and municipal text. We experiment with augmenting training data and corpus choice for this pivot-based approach. We compare the results to a baseline and an end-to-end LLM approach using the GPT 3.5 Turbo model. Our evaluation shows that, while we can substantially improve the results of the pivot pipeline, the zero-shot end-to-end GPT-based simplification performs better on all metrics. Our work shows how an existing pivot-based pipeline can be improved for simplifying Dutch medical text. Moreover, we provide baselines for the comparison in the domain of Dutch municipal text and make our corresponding evaluation dataset publicly available.
%U https://aclanthology.org/2024.lrec-main.199
%P 2217-2226
Markdown (Informal)
[Benchmarking the Simplification of Dutch Municipal Text](https://aclanthology.org/2024.lrec-main.199) (Vlantis et al., LREC-COLING 2024)
ACL
- Daniel Vlantis, Iva Gornishka, and Shuai Wang. 2024. Benchmarking the Simplification of Dutch Municipal Text. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2217–2226, Torino, Italia. ELRA and ICCL.