@inproceedings{degraeuwe-goethals-2024-lexcomspal2-lexical,
title = "{L}ex{C}om{S}pa{L}2: A Lexical Complexity Corpus for {S}panish as a Foreign Language",
author = "Degraeuwe, Jasper and
Goethals, Patrick",
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.912",
pages = "10432--10447",
abstract = "We present LexComSpaL2, a novel corpus which can be employed to train personalised word-level difficulty classifiers for learners of Spanish as a foreign/second language (L2). The dataset contains 2,240 in-context target words with the corresponding difficulty judgements of 26 Dutch-speaking students who are learning Spanish as an L2, resulting in a total of 58,240 annotations. The target words are divided over 200 sentences from 4 different domains (economics, health, law, and migration) and have been selected based on their suitability to be included in L2 learning materials. As our annotation scheme, we use a customised version of the 5-point lexical complexity prediction scale (Shardlow et al., 2020), tailored to the vocabulary knowledge continuum (which ranges from no knowledge over receptive mastery to productive mastery; Schmitt, 2019). With LexComSpaL2, we aim to address the lack of relevant data for multi-category difficult prediction at word level for L2 learners of other languages than English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="degraeuwe-goethals-2024-lexcomspal2-lexical">
<titleInfo>
<title>LexComSpaL2: A Lexical Complexity Corpus for Spanish as a Foreign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="family">Degraeuwe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Goethals</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>We present LexComSpaL2, a novel corpus which can be employed to train personalised word-level difficulty classifiers for learners of Spanish as a foreign/second language (L2). The dataset contains 2,240 in-context target words with the corresponding difficulty judgements of 26 Dutch-speaking students who are learning Spanish as an L2, resulting in a total of 58,240 annotations. The target words are divided over 200 sentences from 4 different domains (economics, health, law, and migration) and have been selected based on their suitability to be included in L2 learning materials. As our annotation scheme, we use a customised version of the 5-point lexical complexity prediction scale (Shardlow et al., 2020), tailored to the vocabulary knowledge continuum (which ranges from no knowledge over receptive mastery to productive mastery; Schmitt, 2019). With LexComSpaL2, we aim to address the lack of relevant data for multi-category difficult prediction at word level for L2 learners of other languages than English.</abstract>
<identifier type="citekey">degraeuwe-goethals-2024-lexcomspal2-lexical</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.912</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10432</start>
<end>10447</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexComSpaL2: A Lexical Complexity Corpus for Spanish as a Foreign Language
%A Degraeuwe, Jasper
%A Goethals, Patrick
%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 degraeuwe-goethals-2024-lexcomspal2-lexical
%X We present LexComSpaL2, a novel corpus which can be employed to train personalised word-level difficulty classifiers for learners of Spanish as a foreign/second language (L2). The dataset contains 2,240 in-context target words with the corresponding difficulty judgements of 26 Dutch-speaking students who are learning Spanish as an L2, resulting in a total of 58,240 annotations. The target words are divided over 200 sentences from 4 different domains (economics, health, law, and migration) and have been selected based on their suitability to be included in L2 learning materials. As our annotation scheme, we use a customised version of the 5-point lexical complexity prediction scale (Shardlow et al., 2020), tailored to the vocabulary knowledge continuum (which ranges from no knowledge over receptive mastery to productive mastery; Schmitt, 2019). With LexComSpaL2, we aim to address the lack of relevant data for multi-category difficult prediction at word level for L2 learners of other languages than English.
%U https://aclanthology.org/2024.lrec-main.912
%P 10432-10447
Markdown (Informal)
[LexComSpaL2: A Lexical Complexity Corpus for Spanish as a Foreign Language](https://aclanthology.org/2024.lrec-main.912) (Degraeuwe & Goethals, LREC-COLING 2024)
ACL