@inproceedings{yang-etal-2020-enhancing,
title = "Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking",
author = "Yang, Ruosong and
Cao, Jiannong and
Wen, Zhiyuan and
Wu, Youzheng and
He, Xiaodong",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.141",
doi = "10.18653/v1/2020.findings-emnlp.141",
pages = "1560--1569",
abstract = "Automated Essay Scoring (AES) is a critical text regression task that automatically assigns scores to essays based on their writing quality. Recently, the performance of sentence prediction tasks has been largely improved by using Pre-trained Language Models via fusing representations from different layers, constructing an auxiliary sentence, using multi-task learning, etc. However, to solve the AES task, previous works utilize shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss, respectively. Since shallow neural networks trained on limited samples show poor performance to capture deep semantic of texts. And without an accurate scoring function, ranking loss and regression loss measures two different aspects of the calculated scores. To improve AES{'}s performance, we find a new way to fine-tune pre-trained language models with multiple losses of the same task. In this paper, we propose to utilize a pre-trained language model to learn text representations first. With scores calculated from the representations, mean square error loss and the batch-wise ListNet loss with dynamic weights constrain the scores simultaneously. We utilize Quadratic Weighted Kappa to evaluate our model on the Automated Student Assessment Prize dataset. Our model outperforms not only state-of-the-art neural models near 3 percent but also the latest statistic model. Especially on the two narrative prompts, our model performs much better than all other state-of-the-art models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-enhancing">
<titleInfo>
<title>Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiannong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youzheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Automated Essay Scoring (AES) is a critical text regression task that automatically assigns scores to essays based on their writing quality. Recently, the performance of sentence prediction tasks has been largely improved by using Pre-trained Language Models via fusing representations from different layers, constructing an auxiliary sentence, using multi-task learning, etc. However, to solve the AES task, previous works utilize shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss, respectively. Since shallow neural networks trained on limited samples show poor performance to capture deep semantic of texts. And without an accurate scoring function, ranking loss and regression loss measures two different aspects of the calculated scores. To improve AES’s performance, we find a new way to fine-tune pre-trained language models with multiple losses of the same task. In this paper, we propose to utilize a pre-trained language model to learn text representations first. With scores calculated from the representations, mean square error loss and the batch-wise ListNet loss with dynamic weights constrain the scores simultaneously. We utilize Quadratic Weighted Kappa to evaluate our model on the Automated Student Assessment Prize dataset. Our model outperforms not only state-of-the-art neural models near 3 percent but also the latest statistic model. Especially on the two narrative prompts, our model performs much better than all other state-of-the-art models.</abstract>
<identifier type="citekey">yang-etal-2020-enhancing</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.141</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.141</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1560</start>
<end>1569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking
%A Yang, Ruosong
%A Cao, Jiannong
%A Wen, Zhiyuan
%A Wu, Youzheng
%A He, Xiaodong
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yang-etal-2020-enhancing
%X Automated Essay Scoring (AES) is a critical text regression task that automatically assigns scores to essays based on their writing quality. Recently, the performance of sentence prediction tasks has been largely improved by using Pre-trained Language Models via fusing representations from different layers, constructing an auxiliary sentence, using multi-task learning, etc. However, to solve the AES task, previous works utilize shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss, respectively. Since shallow neural networks trained on limited samples show poor performance to capture deep semantic of texts. And without an accurate scoring function, ranking loss and regression loss measures two different aspects of the calculated scores. To improve AES’s performance, we find a new way to fine-tune pre-trained language models with multiple losses of the same task. In this paper, we propose to utilize a pre-trained language model to learn text representations first. With scores calculated from the representations, mean square error loss and the batch-wise ListNet loss with dynamic weights constrain the scores simultaneously. We utilize Quadratic Weighted Kappa to evaluate our model on the Automated Student Assessment Prize dataset. Our model outperforms not only state-of-the-art neural models near 3 percent but also the latest statistic model. Especially on the two narrative prompts, our model performs much better than all other state-of-the-art models.
%R 10.18653/v1/2020.findings-emnlp.141
%U https://aclanthology.org/2020.findings-emnlp.141
%U https://doi.org/10.18653/v1/2020.findings-emnlp.141
%P 1560-1569
Markdown (Informal)
[Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking](https://aclanthology.org/2020.findings-emnlp.141) (Yang et al., Findings 2020)
ACL