@inproceedings{sastre-etal-2024-retuyt,
title = "{RETUYT}-{INCO} at {MLSP} 2024: Experiments on Language Simplification using Embeddings, Classifiers and Large Language Models",
author = "Sastre, Ignacio and
Alfonso, Leandro and
Fleitas, Facundo and
Gil, Federico and
Lucas, Andr{\'e}s and
Spoturno, Tom{\'a}s and
G{\'o}ngora, Santiago and
Ros{\'a}, Aiala and
Chiruzzo, Luis",
editor = {Kochmar, Ekaterina and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bea-1.56/",
pages = "618--626",
abstract = "In this paper we present the participation of the RETUYT-INCO team at the BEA-MLSP 2024 shared task. We followed different approaches, from Multilayer Perceptron models with word embeddings to Large Language Models fine-tuned on different datasets: already existing, crowd-annotated, and synthetic.Our best models are based on fine-tuning Mistral-7B, either with a manually annotated dataset or with synthetic data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sastre-etal-2024-retuyt">
<titleInfo>
<title>RETUYT-INCO at MLSP 2024: Experiments on Language Simplification using Embeddings, Classifiers and Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Sastre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leandro</namePart>
<namePart type="family">Alfonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="family">Fleitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Gil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrés</namePart>
<namePart type="family">Lucas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomás</namePart>
<namePart type="family">Spoturno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Góngora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present the participation of the RETUYT-INCO team at the BEA-MLSP 2024 shared task. We followed different approaches, from Multilayer Perceptron models with word embeddings to Large Language Models fine-tuned on different datasets: already existing, crowd-annotated, and synthetic.Our best models are based on fine-tuning Mistral-7B, either with a manually annotated dataset or with synthetic data.</abstract>
<identifier type="citekey">sastre-etal-2024-retuyt</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.56/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>618</start>
<end>626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RETUYT-INCO at MLSP 2024: Experiments on Language Simplification using Embeddings, Classifiers and Large Language Models
%A Sastre, Ignacio
%A Alfonso, Leandro
%A Fleitas, Facundo
%A Gil, Federico
%A Lucas, Andrés
%A Spoturno, Tomás
%A Góngora, Santiago
%A Rosá, Aiala
%A Chiruzzo, Luis
%Y Kochmar, Ekaterina
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F sastre-etal-2024-retuyt
%X In this paper we present the participation of the RETUYT-INCO team at the BEA-MLSP 2024 shared task. We followed different approaches, from Multilayer Perceptron models with word embeddings to Large Language Models fine-tuned on different datasets: already existing, crowd-annotated, and synthetic.Our best models are based on fine-tuning Mistral-7B, either with a manually annotated dataset or with synthetic data.
%U https://aclanthology.org/2024.bea-1.56/
%P 618-626
Markdown (Informal)
[RETUYT-INCO at MLSP 2024: Experiments on Language Simplification using Embeddings, Classifiers and Large Language Models](https://aclanthology.org/2024.bea-1.56/) (Sastre et al., BEA 2024)
ACL
- Ignacio Sastre, Leandro Alfonso, Facundo Fleitas, Federico Gil, Andrés Lucas, Tomás Spoturno, Santiago Góngora, Aiala Rosá, and Luis Chiruzzo. 2024. RETUYT-INCO at MLSP 2024: Experiments on Language Simplification using Embeddings, Classifiers and Large Language Models. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), pages 618–626, Mexico City, Mexico. Association for Computational Linguistics.