@inproceedings{tornqvist-etal-2023-exasag,
title = "{E}x{ASAG}: Explainable Framework for Automatic Short Answer Grading",
author = "Tornqvist, Maximilian and
Mahamud, Mosleh and
Mendez Guzman, Erick and
Farazouli, Alexandra",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.29",
doi = "10.18653/v1/2023.bea-1.29",
pages = "361--371",
abstract = "As in other NLP tasks, Automatic Short Answer Grading (ASAG) systems have evolved from using rule-based and interpretable machine learning models to utilizing deep learning architectures to boost accuracy. Since proper feedback is critical to student assessment, explainability will be crucial for deploying ASAG in real-world applications. This paper proposes a framework to generate explainable outcomes for assessing question-answer pairs of a Data Mining course in a binary manner. Our framework utilizes a fine-tuned Transformer-based classifier and an explainability module using SHAP or Integrated Gradients to generate language explanations for each prediction. We assess the outcome of our framework by calculating accuracy-based metrics for classification performance. Furthermore, we evaluate the quality of the explanations by measuring their agreement with human-annotated justifications using Intersection-Over-Union at a token level to derive a plausibility score. Despite the relatively limited sample, results show that our framework derives explanations that are, to some degree, aligned with domain-expert judgment. Furthermore, both explainability methods perform similarly in their agreement with human-annotated explanations. A natural progression of our work is to analyze the use of our explainable ASAG framework on a larger sample to determine the feasibility of implementing a pilot study in a real-world setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tornqvist-etal-2023-exasag">
<titleInfo>
<title>ExASAG: Explainable Framework for Automatic Short Answer Grading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Tornqvist</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mosleh</namePart>
<namePart type="family">Mahamud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erick</namePart>
<namePart type="family">Mendez Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Farazouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</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">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">Nitin</namePart>
<namePart type="family">Madnani</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>
<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">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As in other NLP tasks, Automatic Short Answer Grading (ASAG) systems have evolved from using rule-based and interpretable machine learning models to utilizing deep learning architectures to boost accuracy. Since proper feedback is critical to student assessment, explainability will be crucial for deploying ASAG in real-world applications. This paper proposes a framework to generate explainable outcomes for assessing question-answer pairs of a Data Mining course in a binary manner. Our framework utilizes a fine-tuned Transformer-based classifier and an explainability module using SHAP or Integrated Gradients to generate language explanations for each prediction. We assess the outcome of our framework by calculating accuracy-based metrics for classification performance. Furthermore, we evaluate the quality of the explanations by measuring their agreement with human-annotated justifications using Intersection-Over-Union at a token level to derive a plausibility score. Despite the relatively limited sample, results show that our framework derives explanations that are, to some degree, aligned with domain-expert judgment. Furthermore, both explainability methods perform similarly in their agreement with human-annotated explanations. A natural progression of our work is to analyze the use of our explainable ASAG framework on a larger sample to determine the feasibility of implementing a pilot study in a real-world setting.</abstract>
<identifier type="citekey">tornqvist-etal-2023-exasag</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.29</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.29</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>361</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExASAG: Explainable Framework for Automatic Short Answer Grading
%A Tornqvist, Maximilian
%A Mahamud, Mosleh
%A Mendez Guzman, Erick
%A Farazouli, Alexandra
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tornqvist-etal-2023-exasag
%X As in other NLP tasks, Automatic Short Answer Grading (ASAG) systems have evolved from using rule-based and interpretable machine learning models to utilizing deep learning architectures to boost accuracy. Since proper feedback is critical to student assessment, explainability will be crucial for deploying ASAG in real-world applications. This paper proposes a framework to generate explainable outcomes for assessing question-answer pairs of a Data Mining course in a binary manner. Our framework utilizes a fine-tuned Transformer-based classifier and an explainability module using SHAP or Integrated Gradients to generate language explanations for each prediction. We assess the outcome of our framework by calculating accuracy-based metrics for classification performance. Furthermore, we evaluate the quality of the explanations by measuring their agreement with human-annotated justifications using Intersection-Over-Union at a token level to derive a plausibility score. Despite the relatively limited sample, results show that our framework derives explanations that are, to some degree, aligned with domain-expert judgment. Furthermore, both explainability methods perform similarly in their agreement with human-annotated explanations. A natural progression of our work is to analyze the use of our explainable ASAG framework on a larger sample to determine the feasibility of implementing a pilot study in a real-world setting.
%R 10.18653/v1/2023.bea-1.29
%U https://aclanthology.org/2023.bea-1.29
%U https://doi.org/10.18653/v1/2023.bea-1.29
%P 361-371
Markdown (Informal)
[ExASAG: Explainable Framework for Automatic Short Answer Grading](https://aclanthology.org/2023.bea-1.29) (Tornqvist et al., BEA 2023)
ACL
- Maximilian Tornqvist, Mosleh Mahamud, Erick Mendez Guzman, and Alexandra Farazouli. 2023. ExASAG: Explainable Framework for Automatic Short Answer Grading. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 361–371, Toronto, Canada. Association for Computational Linguistics.