@inproceedings{cristea-nisioi-2024-machine,
title = "Archaeology at MLSP 2024: Machine Translation for Lexical Complexity Prediction and Lexical Simplification",
author = "Cristea, Petru and
Nisioi, Sergiu",
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-1.55",
pages = "610--617",
abstract = "We present the submissions of team Archaeology for the Lexical Simplification and Lexical Complexity Prediction Shared Tasks at BEA2024. Our approach for this shared task consists in creating two pipelines for generating lexical substitutions and estimating the complexity: one using machine translation texts into English and one using the original language.For the LCP subtask, our xgb regressor is trained with engineered features (based primarily on English language resources) and shallow word structure features. For the LS subtask we use a locally-executed quantized LLM to generate candidates and sort them by complexity score computed using the pipeline designed for LCP.These pipelines provide distinct perspectives on the lexical simplification process, offering insights into the efficacy and limitations of employing Machine Translation versus direct processing on the original language data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cristea-nisioi-2024-machine">
<titleInfo>
<title>Archaeology at MLSP 2024: Machine Translation for Lexical Complexity Prediction and Lexical Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petru</namePart>
<namePart type="family">Cristea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergiu</namePart>
<namePart type="family">Nisioi</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>We present the submissions of team Archaeology for the Lexical Simplification and Lexical Complexity Prediction Shared Tasks at BEA2024. Our approach for this shared task consists in creating two pipelines for generating lexical substitutions and estimating the complexity: one using machine translation texts into English and one using the original language.For the LCP subtask, our xgb regressor is trained with engineered features (based primarily on English language resources) and shallow word structure features. For the LS subtask we use a locally-executed quantized LLM to generate candidates and sort them by complexity score computed using the pipeline designed for LCP.These pipelines provide distinct perspectives on the lexical simplification process, offering insights into the efficacy and limitations of employing Machine Translation versus direct processing on the original language data.</abstract>
<identifier type="citekey">cristea-nisioi-2024-machine</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.55</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>610</start>
<end>617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Archaeology at MLSP 2024: Machine Translation for Lexical Complexity Prediction and Lexical Simplification
%A Cristea, Petru
%A Nisioi, Sergiu
%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 cristea-nisioi-2024-machine
%X We present the submissions of team Archaeology for the Lexical Simplification and Lexical Complexity Prediction Shared Tasks at BEA2024. Our approach for this shared task consists in creating two pipelines for generating lexical substitutions and estimating the complexity: one using machine translation texts into English and one using the original language.For the LCP subtask, our xgb regressor is trained with engineered features (based primarily on English language resources) and shallow word structure features. For the LS subtask we use a locally-executed quantized LLM to generate candidates and sort them by complexity score computed using the pipeline designed for LCP.These pipelines provide distinct perspectives on the lexical simplification process, offering insights into the efficacy and limitations of employing Machine Translation versus direct processing on the original language data.
%U https://aclanthology.org/2024.bea-1.55
%P 610-617
Markdown (Informal)
[Archaeology at MLSP 2024: Machine Translation for Lexical Complexity Prediction and Lexical Simplification](https://aclanthology.org/2024.bea-1.55) (Cristea & Nisioi, BEA 2024)
ACL