@inproceedings{scalercio-etal-2024-enhancing,
title = "Enhancing Sentence Simplification in {P}ortuguese: Leveraging Paraphrases, Context, and Linguistic Features",
author = "Scalercio, Arthur and
Finatto, Maria and
Paes, Aline",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.895/",
doi = "10.18653/v1/2024.findings-acl.895",
pages = "15076--15091",
abstract = "Automatic text simplification focuses on transforming texts into a more comprehensible version without sacrificing their precision. However, automatic methods usually require (paired) datasets that can be rather scarce in languages other than English. This paper presents a new approach to automatic sentence simplification that leverages paraphrases, context, and linguistic attributes to overcome the absence of paired texts in Portuguese.We frame the simplification problem as a textual style transfer task and learn a style representation using the sentences around the target sentence in the document and its linguistic attributes. Moreover, unlike most unsupervised approaches that require style-labeled training data, we fine-tune strong pre-trained models using sentence-level paraphrases instead of annotated data. Our experiments show that our model achieves remarkable results, surpassing the current state-of-the-art (BART+ACCESS) while competitively matching a Large Language Model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scalercio-etal-2024-enhancing">
<titleInfo>
<title>Enhancing Sentence Simplification in Portuguese: Leveraging Paraphrases, Context, and Linguistic Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Scalercio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Finatto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic text simplification focuses on transforming texts into a more comprehensible version without sacrificing their precision. However, automatic methods usually require (paired) datasets that can be rather scarce in languages other than English. This paper presents a new approach to automatic sentence simplification that leverages paraphrases, context, and linguistic attributes to overcome the absence of paired texts in Portuguese.We frame the simplification problem as a textual style transfer task and learn a style representation using the sentences around the target sentence in the document and its linguistic attributes. Moreover, unlike most unsupervised approaches that require style-labeled training data, we fine-tune strong pre-trained models using sentence-level paraphrases instead of annotated data. Our experiments show that our model achieves remarkable results, surpassing the current state-of-the-art (BART+ACCESS) while competitively matching a Large Language Model.</abstract>
<identifier type="citekey">scalercio-etal-2024-enhancing</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.895</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.895/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>15076</start>
<end>15091</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Sentence Simplification in Portuguese: Leveraging Paraphrases, Context, and Linguistic Features
%A Scalercio, Arthur
%A Finatto, Maria
%A Paes, Aline
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F scalercio-etal-2024-enhancing
%X Automatic text simplification focuses on transforming texts into a more comprehensible version without sacrificing their precision. However, automatic methods usually require (paired) datasets that can be rather scarce in languages other than English. This paper presents a new approach to automatic sentence simplification that leverages paraphrases, context, and linguistic attributes to overcome the absence of paired texts in Portuguese.We frame the simplification problem as a textual style transfer task and learn a style representation using the sentences around the target sentence in the document and its linguistic attributes. Moreover, unlike most unsupervised approaches that require style-labeled training data, we fine-tune strong pre-trained models using sentence-level paraphrases instead of annotated data. Our experiments show that our model achieves remarkable results, surpassing the current state-of-the-art (BART+ACCESS) while competitively matching a Large Language Model.
%R 10.18653/v1/2024.findings-acl.895
%U https://aclanthology.org/2024.findings-acl.895/
%U https://doi.org/10.18653/v1/2024.findings-acl.895
%P 15076-15091
Markdown (Informal)
[Enhancing Sentence Simplification in Portuguese: Leveraging Paraphrases, Context, and Linguistic Features](https://aclanthology.org/2024.findings-acl.895/) (Scalercio et al., Findings 2024)
ACL