@inproceedings{robertson-etal-2022-tallvocabl2fi,
title = "{T}all{V}ocab{L}2{F}i: A Tall Dataset of 15 {F}innish {L}2 Learners{'} Vocabulary",
author = {Robertson, Frankie and
Chang, Li-Hsin and
S{\"o}yrinki, Sini},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.685",
pages = "6377--6386",
abstract = "Previous work concerning measurement of second language learners has tended to focus on the knowledge of small numbers of words, often geared towards measuring vocabulary size. This paper presents a {``}tall{''} dataset containing information about a few learners{'} knowledge of many words, suitable for evaluating Vocabulary Inventory Prediction (VIP) techniques, including those based on Computerised Adaptive Testing (CAT). In comparison to previous comparable datasets, the learners are from varied backgrounds, so as to reduce the risk of overfitting when used for machine learning based VIP. The dataset contains both a self-rating test and a translation test, used to derive a measure of reliability for learner responses. The dataset creation process is documented, and the relationship between variables concerning the participants, such as their completion time, their language ability level, and the triangulated reliability of their self-assessment responses, are analysed. The word list is constructed by taking into account the extensive derivation morphology of Finnish, and infrequent words are included in order to account for explanatory variables beyond word frequency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robertson-etal-2022-tallvocabl2fi">
<titleInfo>
<title>TallVocabL2Fi: A Tall Dataset of 15 Finnish L2 Learners’ Vocabulary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frankie</namePart>
<namePart type="family">Robertson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li-Hsin</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sini</namePart>
<namePart type="family">Söyrinki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work concerning measurement of second language learners has tended to focus on the knowledge of small numbers of words, often geared towards measuring vocabulary size. This paper presents a “tall” dataset containing information about a few learners’ knowledge of many words, suitable for evaluating Vocabulary Inventory Prediction (VIP) techniques, including those based on Computerised Adaptive Testing (CAT). In comparison to previous comparable datasets, the learners are from varied backgrounds, so as to reduce the risk of overfitting when used for machine learning based VIP. The dataset contains both a self-rating test and a translation test, used to derive a measure of reliability for learner responses. The dataset creation process is documented, and the relationship between variables concerning the participants, such as their completion time, their language ability level, and the triangulated reliability of their self-assessment responses, are analysed. The word list is constructed by taking into account the extensive derivation morphology of Finnish, and infrequent words are included in order to account for explanatory variables beyond word frequency.</abstract>
<identifier type="citekey">robertson-etal-2022-tallvocabl2fi</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.685</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6377</start>
<end>6386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TallVocabL2Fi: A Tall Dataset of 15 Finnish L2 Learners’ Vocabulary
%A Robertson, Frankie
%A Chang, Li-Hsin
%A Söyrinki, Sini
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F robertson-etal-2022-tallvocabl2fi
%X Previous work concerning measurement of second language learners has tended to focus on the knowledge of small numbers of words, often geared towards measuring vocabulary size. This paper presents a “tall” dataset containing information about a few learners’ knowledge of many words, suitable for evaluating Vocabulary Inventory Prediction (VIP) techniques, including those based on Computerised Adaptive Testing (CAT). In comparison to previous comparable datasets, the learners are from varied backgrounds, so as to reduce the risk of overfitting when used for machine learning based VIP. The dataset contains both a self-rating test and a translation test, used to derive a measure of reliability for learner responses. The dataset creation process is documented, and the relationship between variables concerning the participants, such as their completion time, their language ability level, and the triangulated reliability of their self-assessment responses, are analysed. The word list is constructed by taking into account the extensive derivation morphology of Finnish, and infrequent words are included in order to account for explanatory variables beyond word frequency.
%U https://aclanthology.org/2022.lrec-1.685
%P 6377-6386
Markdown (Informal)
[TallVocabL2Fi: A Tall Dataset of 15 Finnish L2 Learners’ Vocabulary](https://aclanthology.org/2022.lrec-1.685) (Robertson et al., LREC 2022)
ACL