@inproceedings{yancey-etal-2024-bert,
title = "{BERT}-{IRT}: Accelerating Item Piloting with {BERT} Embeddings and Explainable {IRT} Models",
author = "Yancey, Kevin P. and
Runge, Andrew and
LaFlair, Geoffrey and
Mulcaire, Phoebe",
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-1.35",
pages = "428--438",
abstract = "Estimating item parameters (e.g., the difficulty of a question) is an important part of modern high-stakes tests. Conventional methods require lengthy pilots to collect response data from a representative population of test-takers. The need for these pilots limit item bank size and how often those item banks can be refreshed, impacting test security, while increasing costs needed to support the test and taking up the test-taker{'}s valuable time. Our paper presents a novel explanatory item response theory (IRT) model, BERT-IRT, that has been used on the Duolingo English Test (DET), a high-stakes test of English, to reduce the length of pilots by a factor of 10. Our evaluation shows how the model uses BERT embeddings and engineered NLP features to accelerate item piloting without sacrificing criterion validity or reliability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yancey-etal-2024-bert">
<titleInfo>
<title>BERT-IRT: Accelerating Item Piloting with BERT Embeddings and Explainable IRT Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Yancey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Runge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geoffrey</namePart>
<namePart type="family">LaFlair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phoebe</namePart>
<namePart type="family">Mulcaire</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>Estimating item parameters (e.g., the difficulty of a question) is an important part of modern high-stakes tests. Conventional methods require lengthy pilots to collect response data from a representative population of test-takers. The need for these pilots limit item bank size and how often those item banks can be refreshed, impacting test security, while increasing costs needed to support the test and taking up the test-taker’s valuable time. Our paper presents a novel explanatory item response theory (IRT) model, BERT-IRT, that has been used on the Duolingo English Test (DET), a high-stakes test of English, to reduce the length of pilots by a factor of 10. Our evaluation shows how the model uses BERT embeddings and engineered NLP features to accelerate item piloting without sacrificing criterion validity or reliability.</abstract>
<identifier type="citekey">yancey-etal-2024-bert</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.35</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>428</start>
<end>438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT-IRT: Accelerating Item Piloting with BERT Embeddings and Explainable IRT Models
%A Yancey, Kevin P.
%A Runge, Andrew
%A LaFlair, Geoffrey
%A Mulcaire, Phoebe
%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 yancey-etal-2024-bert
%X Estimating item parameters (e.g., the difficulty of a question) is an important part of modern high-stakes tests. Conventional methods require lengthy pilots to collect response data from a representative population of test-takers. The need for these pilots limit item bank size and how often those item banks can be refreshed, impacting test security, while increasing costs needed to support the test and taking up the test-taker’s valuable time. Our paper presents a novel explanatory item response theory (IRT) model, BERT-IRT, that has been used on the Duolingo English Test (DET), a high-stakes test of English, to reduce the length of pilots by a factor of 10. Our evaluation shows how the model uses BERT embeddings and engineered NLP features to accelerate item piloting without sacrificing criterion validity or reliability.
%U https://aclanthology.org/2024.bea-1.35
%P 428-438
Markdown (Informal)
[BERT-IRT: Accelerating Item Piloting with BERT Embeddings and Explainable IRT Models](https://aclanthology.org/2024.bea-1.35) (Yancey et al., BEA 2024)
ACL