@inproceedings{suen-etal-2023-acta,
title = "{ACTA}: Short-Answer Grading in High-Stakes Medical Exams",
author = "Suen, King Yiu and
Yaneva, Victoria and
Ha, Le An and
Mee, Janet and
Zhou, Yiyun and
Harik, Polina",
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-1.36",
doi = "10.18653/v1/2023.bea-1.36",
pages = "443--447",
abstract = "This paper presents the ACTA system, which performs automated short-answer grading in the domain of high-stakes medical exams. The system builds upon previous work on neural similarity-based grading approaches by applying these to the medical domain and utilizing contrastive learning as a means to optimize the similarity metric. ACTA is evaluated against three strong baselines and is developed in alignment with operational needs, where low-confidence responses are flagged for human review. Learning curves are explored to understand the effects of training data on performance. The results demonstrate that ACTA leads to substantially lower number of responses being flagged for human review, while maintaining high classification accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suen-etal-2023-acta">
<titleInfo>
<title>ACTA: Short-Answer Grading in High-Stakes Medical Exams</title>
</titleInfo>
<name type="personal">
<namePart type="given">King</namePart>
<namePart type="given">Yiu</namePart>
<namePart type="family">Suen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">An</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janet</namePart>
<namePart type="family">Mee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Polina</namePart>
<namePart type="family">Harik</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>This paper presents the ACTA system, which performs automated short-answer grading in the domain of high-stakes medical exams. The system builds upon previous work on neural similarity-based grading approaches by applying these to the medical domain and utilizing contrastive learning as a means to optimize the similarity metric. ACTA is evaluated against three strong baselines and is developed in alignment with operational needs, where low-confidence responses are flagged for human review. Learning curves are explored to understand the effects of training data on performance. The results demonstrate that ACTA leads to substantially lower number of responses being flagged for human review, while maintaining high classification accuracy.</abstract>
<identifier type="citekey">suen-etal-2023-acta</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.36</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.36</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>443</start>
<end>447</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ACTA: Short-Answer Grading in High-Stakes Medical Exams
%A Suen, King Yiu
%A Yaneva, Victoria
%A Ha, Le An
%A Mee, Janet
%A Zhou, Yiyun
%A Harik, Polina
%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 suen-etal-2023-acta
%X This paper presents the ACTA system, which performs automated short-answer grading in the domain of high-stakes medical exams. The system builds upon previous work on neural similarity-based grading approaches by applying these to the medical domain and utilizing contrastive learning as a means to optimize the similarity metric. ACTA is evaluated against three strong baselines and is developed in alignment with operational needs, where low-confidence responses are flagged for human review. Learning curves are explored to understand the effects of training data on performance. The results demonstrate that ACTA leads to substantially lower number of responses being flagged for human review, while maintaining high classification accuracy.
%R 10.18653/v1/2023.bea-1.36
%U https://aclanthology.org/2023.bea-1.36
%U https://doi.org/10.18653/v1/2023.bea-1.36
%P 443-447
Markdown (Informal)
[ACTA: Short-Answer Grading in High-Stakes Medical Exams](https://aclanthology.org/2023.bea-1.36) (Suen et al., BEA 2023)
ACL
- King Yiu Suen, Victoria Yaneva, Le An Ha, Janet Mee, Yiyun Zhou, and Polina Harik. 2023. ACTA: Short-Answer Grading in High-Stakes Medical Exams. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 443–447, Toronto, Canada. Association for Computational Linguistics.