@inproceedings{shardlow-etal-2024-multilingual,
title = "A Multilingual Survey of Recent Lexical Complexity Prediction Resources through the Recommendations of the Complex 2.0 Framework",
author = "Shardlow, Matthew and
North, Kai and
Zampieri, Marcos",
editor = "Nunzio, Giorgio Maria Di and
Vezzani, Federica and
Ermakova, Liana and
Azarbonyad, Hosein and
Kamps, Jaap",
booktitle = "Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.determit-1.5",
pages = "51--59",
abstract = "Lexical complexity prediction is the NLP task aimed at using machine learning to predict the difficulty of a target word in context for a given user or user group. Multiple datasets exist for lexical complexity prediction, many of which have been published recently in diverse languages. In this survey, we discuss nine recent datasets (2018-2024) all of which provide lexical complexity prediction annotations. Particularly, we identified eight languages (French, Spanish, Chinese, German, Russian, Japanese, Turkish and Portuguese) with at least one lexical complexity dataset. We do not consider the English datasets, which have already received significant treatment elsewhere in the literature. To survey these datasets, we use the recommendations of the Complex 2.0 Framework (Shardlow et al., 2022), identifying how the datasets differ along the following dimensions: annotation scale, context, multiple token instances, multiple token annotations, diverse annotators. We conclude with future research challenges arising from our survey of existing lexical complexity prediction datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shardlow-etal-2024-multilingual">
<titleInfo>
<title>A Multilingual Survey of Recent Lexical Complexity Prediction Resources through the Recommendations of the Complex 2.0 Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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 Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giorgio</namePart>
<namePart type="given">Maria</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Nunzio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Vezzani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liana</namePart>
<namePart type="family">Ermakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Azarbonyad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Kamps</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>Lexical complexity prediction is the NLP task aimed at using machine learning to predict the difficulty of a target word in context for a given user or user group. Multiple datasets exist for lexical complexity prediction, many of which have been published recently in diverse languages. In this survey, we discuss nine recent datasets (2018-2024) all of which provide lexical complexity prediction annotations. Particularly, we identified eight languages (French, Spanish, Chinese, German, Russian, Japanese, Turkish and Portuguese) with at least one lexical complexity dataset. We do not consider the English datasets, which have already received significant treatment elsewhere in the literature. To survey these datasets, we use the recommendations of the Complex 2.0 Framework (Shardlow et al., 2022), identifying how the datasets differ along the following dimensions: annotation scale, context, multiple token instances, multiple token annotations, diverse annotators. We conclude with future research challenges arising from our survey of existing lexical complexity prediction datasets.</abstract>
<identifier type="citekey">shardlow-etal-2024-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.determit-1.5</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>51</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multilingual Survey of Recent Lexical Complexity Prediction Resources through the Recommendations of the Complex 2.0 Framework
%A Shardlow, Matthew
%A North, Kai
%A Zampieri, Marcos
%Y Nunzio, Giorgio Maria Di
%Y Vezzani, Federica
%Y Ermakova, Liana
%Y Azarbonyad, Hosein
%Y Kamps, Jaap
%S Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shardlow-etal-2024-multilingual
%X Lexical complexity prediction is the NLP task aimed at using machine learning to predict the difficulty of a target word in context for a given user or user group. Multiple datasets exist for lexical complexity prediction, many of which have been published recently in diverse languages. In this survey, we discuss nine recent datasets (2018-2024) all of which provide lexical complexity prediction annotations. Particularly, we identified eight languages (French, Spanish, Chinese, German, Russian, Japanese, Turkish and Portuguese) with at least one lexical complexity dataset. We do not consider the English datasets, which have already received significant treatment elsewhere in the literature. To survey these datasets, we use the recommendations of the Complex 2.0 Framework (Shardlow et al., 2022), identifying how the datasets differ along the following dimensions: annotation scale, context, multiple token instances, multiple token annotations, diverse annotators. We conclude with future research challenges arising from our survey of existing lexical complexity prediction datasets.
%U https://aclanthology.org/2024.determit-1.5
%P 51-59
Markdown (Informal)
[A Multilingual Survey of Recent Lexical Complexity Prediction Resources through the Recommendations of the Complex 2.0 Framework](https://aclanthology.org/2024.determit-1.5) (Shardlow et al., DeTermIt-WS 2024)
ACL