@inproceedings{wang-etal-2023-aggregating,
title = "Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring",
author = "Wang, Cong and
Jiang, Zhiwei and
Yin, Yafeng and
Cheng, Zifeng and
Ge, Shiping and
Gu, Qing",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.782",
doi = "10.18653/v1/2023.acl-long.782",
pages = "13999--14013",
abstract = "Automated Essay Scoring (AES) aims to evaluate the quality score for input essays. In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training. The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-groundtruth, and then train a neural AES model by learning from the aggregation of these quality signals. To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training. In the DPRA loss, we set a learnable confidence weight for each signal to address the conflicts among signals, and train the neural AES model in a pairwise way to disentangle the cascade effect among partial-order pairs. Experiments on eight prompts of ASPA dataset show that ULRA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both transductive and inductive settings. Further, our approach achieves comparable performance with many existing domain-adapted supervised models, showing the effectiveness of ULRA. The code is available at \url{https://github.com/tenvence/ulra}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-aggregating">
<titleInfo>
<title>Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yafeng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zifeng</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiping</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Gu</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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>Automated Essay Scoring (AES) aims to evaluate the quality score for input essays. In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training. The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-groundtruth, and then train a neural AES model by learning from the aggregation of these quality signals. To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training. In the DPRA loss, we set a learnable confidence weight for each signal to address the conflicts among signals, and train the neural AES model in a pairwise way to disentangle the cascade effect among partial-order pairs. Experiments on eight prompts of ASPA dataset show that ULRA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both transductive and inductive settings. Further, our approach achieves comparable performance with many existing domain-adapted supervised models, showing the effectiveness of ULRA. The code is available at https://github.com/tenvence/ulra.</abstract>
<identifier type="citekey">wang-etal-2023-aggregating</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.782</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.782</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13999</start>
<end>14013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring
%A Wang, Cong
%A Jiang, Zhiwei
%A Yin, Yafeng
%A Cheng, Zifeng
%A Ge, Shiping
%A Gu, Qing
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-aggregating
%X Automated Essay Scoring (AES) aims to evaluate the quality score for input essays. In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training. The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-groundtruth, and then train a neural AES model by learning from the aggregation of these quality signals. To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training. In the DPRA loss, we set a learnable confidence weight for each signal to address the conflicts among signals, and train the neural AES model in a pairwise way to disentangle the cascade effect among partial-order pairs. Experiments on eight prompts of ASPA dataset show that ULRA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both transductive and inductive settings. Further, our approach achieves comparable performance with many existing domain-adapted supervised models, showing the effectiveness of ULRA. The code is available at https://github.com/tenvence/ulra.
%R 10.18653/v1/2023.acl-long.782
%U https://aclanthology.org/2023.acl-long.782
%U https://doi.org/10.18653/v1/2023.acl-long.782
%P 13999-14013
Markdown (Informal)
[Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring](https://aclanthology.org/2023.acl-long.782) (Wang et al., ACL 2023)
ACL