@inproceedings{benedetto-etal-2021-application,
title = "On the application of Transformers for estimating the difficulty of Multiple-Choice Questions from text",
author = "Benedetto, Luca and
Aradelli, Giovanni and
Cremonesi, Paolo and
Cappelli, Andrea and
Giussani, Andrea and
Turrin, Roberto",
editor = "Burstein, Jill and
Horbach, Andrea and
Kochmar, Ekaterina and
Laarmann-Quante, Ronja and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bea-1.16",
pages = "147--157",
abstract = "Classical approaches to question calibration are either subjective or require newly created questions to be deployed before being calibrated. Recent works explored the possibility of estimating question difficulty from text, but did not experiment with the most recent NLP models, in particular Transformers. In this paper, we compare the performance of previous literature with Transformer models experimenting on a public and a private dataset. Our experimental results show that Transformers are capable of outperforming previously proposed models. Moreover, if an additional corpus of related documents is available, Transformers can leverage that information to further improve calibration accuracy. We characterize the dependence of the model performance on some properties of the questions, showing that it performs best on questions ending with a question mark and Multiple-Choice Questions (MCQs) with one correct choice.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benedetto-etal-2021-application">
<titleInfo>
<title>On the application of Transformers for estimating the difficulty of Multiple-Choice Questions from text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Benedetto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Aradelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Cremonesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Cappelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Giussani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Turrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<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">Ekaterina</namePart>
<namePart type="family">Kochmar</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">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Classical approaches to question calibration are either subjective or require newly created questions to be deployed before being calibrated. Recent works explored the possibility of estimating question difficulty from text, but did not experiment with the most recent NLP models, in particular Transformers. In this paper, we compare the performance of previous literature with Transformer models experimenting on a public and a private dataset. Our experimental results show that Transformers are capable of outperforming previously proposed models. Moreover, if an additional corpus of related documents is available, Transformers can leverage that information to further improve calibration accuracy. We characterize the dependence of the model performance on some properties of the questions, showing that it performs best on questions ending with a question mark and Multiple-Choice Questions (MCQs) with one correct choice.</abstract>
<identifier type="citekey">benedetto-etal-2021-application</identifier>
<location>
<url>https://aclanthology.org/2021.bea-1.16</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>147</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the application of Transformers for estimating the difficulty of Multiple-Choice Questions from text
%A Benedetto, Luca
%A Aradelli, Giovanni
%A Cremonesi, Paolo
%A Cappelli, Andrea
%A Giussani, Andrea
%A Turrin, Roberto
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Kochmar, Ekaterina
%Y Laarmann-Quante, Ronja
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F benedetto-etal-2021-application
%X Classical approaches to question calibration are either subjective or require newly created questions to be deployed before being calibrated. Recent works explored the possibility of estimating question difficulty from text, but did not experiment with the most recent NLP models, in particular Transformers. In this paper, we compare the performance of previous literature with Transformer models experimenting on a public and a private dataset. Our experimental results show that Transformers are capable of outperforming previously proposed models. Moreover, if an additional corpus of related documents is available, Transformers can leverage that information to further improve calibration accuracy. We characterize the dependence of the model performance on some properties of the questions, showing that it performs best on questions ending with a question mark and Multiple-Choice Questions (MCQs) with one correct choice.
%U https://aclanthology.org/2021.bea-1.16
%P 147-157
Markdown (Informal)
[On the application of Transformers for estimating the difficulty of Multiple-Choice Questions from text](https://aclanthology.org/2021.bea-1.16) (Benedetto et al., BEA 2021)
ACL