@inproceedings{de-kuthy-etal-2025-automatic,
title = "Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings",
author = "De Kuthy, Kordula and
Girrbach, Leander and
Meurers, Detmar",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar 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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.13/",
doi = "10.18653/v1/2025.bea-1.13",
pages = "175--185",
ISBN = "979-8-89176-270-1",
abstract = "Heterogeneity in student populations poses achallenge in formal education, with adaptivetextbooks offering a potential solution by tai-loring content based on individual learner mod-els. However, creating domain models for text-books typically demands significant manual ef-fort. Recent work by Chau et al. (2021) demon-strated automated concept extraction from dig-ital textbooks, but relied on costly domain-specific manual annotations. This paper in-troduces a novel, scalable method that mini-mizes manual effort by combining contextu-alized word embeddings with weakly super-vised machine learning. Our approach clustersword embeddings from textbooks and identi-fies domain-specific concepts using a machinelearner trained on concept seeds automaticallyextracted from Wikipedia. We evaluate thismethod using 28 economics textbooks, com-paring its performance against a tf-idf baseline,a supervised machine learning baseline, theRAKE keyword extraction method, and humandomain experts. Results demonstrate that ourweakly supervised method effectively balancesaccuracy with reduced annotation effort, offer-ing a practical solution for automated conceptextraction in adaptive learning environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-kuthy-etal-2025-automatic">
<titleInfo>
<title>Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kordula</namePart>
<namePart type="family">De Kuthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leander</namePart>
<namePart type="family">Girrbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Detmar</namePart>
<namePart type="family">Meurers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</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">Bashar</namePart>
<namePart type="family">Alhafni</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">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>Heterogeneity in student populations poses achallenge in formal education, with adaptivetextbooks offering a potential solution by tai-loring content based on individual learner mod-els. However, creating domain models for text-books typically demands significant manual ef-fort. Recent work by Chau et al. (2021) demon-strated automated concept extraction from dig-ital textbooks, but relied on costly domain-specific manual annotations. This paper in-troduces a novel, scalable method that mini-mizes manual effort by combining contextu-alized word embeddings with weakly super-vised machine learning. Our approach clustersword embeddings from textbooks and identi-fies domain-specific concepts using a machinelearner trained on concept seeds automaticallyextracted from Wikipedia. We evaluate thismethod using 28 economics textbooks, com-paring its performance against a tf-idf baseline,a supervised machine learning baseline, theRAKE keyword extraction method, and humandomain experts. Results demonstrate that ourweakly supervised method effectively balancesaccuracy with reduced annotation effort, offer-ing a practical solution for automated conceptextraction in adaptive learning environments.</abstract>
<identifier type="citekey">de-kuthy-etal-2025-automatic</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.13</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.13/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>175</start>
<end>185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings
%A De Kuthy, Kordula
%A Girrbach, Leander
%A Meurers, Detmar
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F de-kuthy-etal-2025-automatic
%X Heterogeneity in student populations poses achallenge in formal education, with adaptivetextbooks offering a potential solution by tai-loring content based on individual learner mod-els. However, creating domain models for text-books typically demands significant manual ef-fort. Recent work by Chau et al. (2021) demon-strated automated concept extraction from dig-ital textbooks, but relied on costly domain-specific manual annotations. This paper in-troduces a novel, scalable method that mini-mizes manual effort by combining contextu-alized word embeddings with weakly super-vised machine learning. Our approach clustersword embeddings from textbooks and identi-fies domain-specific concepts using a machinelearner trained on concept seeds automaticallyextracted from Wikipedia. We evaluate thismethod using 28 economics textbooks, com-paring its performance against a tf-idf baseline,a supervised machine learning baseline, theRAKE keyword extraction method, and humandomain experts. Results demonstrate that ourweakly supervised method effectively balancesaccuracy with reduced annotation effort, offer-ing a practical solution for automated conceptextraction in adaptive learning environments.
%R 10.18653/v1/2025.bea-1.13
%U https://aclanthology.org/2025.bea-1.13/
%U https://doi.org/10.18653/v1/2025.bea-1.13
%P 175-185
Markdown (Informal)
[Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings](https://aclanthology.org/2025.bea-1.13/) (De Kuthy et al., BEA 2025)
ACL