@inproceedings{zhang-litman-2021-essay,
title = "Essay Quality Signals as Weak Supervision for Source-based Essay Scoring",
author = "Zhang, Haoran and
Litman, Diane",
editor = "Burstein, Jill and
Horbach, Andrea and
Kochmar, Ekaterina and
Laarmann-Quante, Ronja and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bea-1.9/",
pages = "85--96",
abstract = "Human essay grading is a laborious task that can consume much time and effort. Automated Essay Scoring (AES) has thus been proposed as a fast and effective solution to the problem of grading student writing at scale. However, because AES typically uses supervised machine learning, a human-graded essay corpus is still required to train the AES model. Unfortunately, such a graded corpus often does not exist, so creating a corpus for machine learning can also be a laborious task. This paper presents an investigation of replacing the use of human-labeled essay grades when training an AES system with two automatically available but weaker signals of essay quality: word count and topic distribution similarity. Experiments using two source-based essay scoring (evidence score) corpora show that while weak supervision does not yield a competitive result when training a neural source-based AES model, it can be used to successfully extract Topical Components (TCs) from a source text, which are required by a supervised feature-based AES model. In particular, results show that feature-based AES performance is comparable with either automatically or manually constructed TCs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-litman-2021-essay">
<titleInfo>
<title>Essay Quality Signals as Weak Supervision for Source-based Essay Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<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">Ekaterina</namePart>
<namePart type="family">Kochmar</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">Claudia</namePart>
<namePart type="family">Leacock</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">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</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">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human essay grading is a laborious task that can consume much time and effort. Automated Essay Scoring (AES) has thus been proposed as a fast and effective solution to the problem of grading student writing at scale. However, because AES typically uses supervised machine learning, a human-graded essay corpus is still required to train the AES model. Unfortunately, such a graded corpus often does not exist, so creating a corpus for machine learning can also be a laborious task. This paper presents an investigation of replacing the use of human-labeled essay grades when training an AES system with two automatically available but weaker signals of essay quality: word count and topic distribution similarity. Experiments using two source-based essay scoring (evidence score) corpora show that while weak supervision does not yield a competitive result when training a neural source-based AES model, it can be used to successfully extract Topical Components (TCs) from a source text, which are required by a supervised feature-based AES model. In particular, results show that feature-based AES performance is comparable with either automatically or manually constructed TCs.</abstract>
<identifier type="citekey">zhang-litman-2021-essay</identifier>
<location>
<url>https://aclanthology.org/2021.bea-1.9/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>85</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Essay Quality Signals as Weak Supervision for Source-based Essay Scoring
%A Zhang, Haoran
%A Litman, Diane
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Kochmar, Ekaterina
%Y Laarmann-Quante, Ronja
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F zhang-litman-2021-essay
%X Human essay grading is a laborious task that can consume much time and effort. Automated Essay Scoring (AES) has thus been proposed as a fast and effective solution to the problem of grading student writing at scale. However, because AES typically uses supervised machine learning, a human-graded essay corpus is still required to train the AES model. Unfortunately, such a graded corpus often does not exist, so creating a corpus for machine learning can also be a laborious task. This paper presents an investigation of replacing the use of human-labeled essay grades when training an AES system with two automatically available but weaker signals of essay quality: word count and topic distribution similarity. Experiments using two source-based essay scoring (evidence score) corpora show that while weak supervision does not yield a competitive result when training a neural source-based AES model, it can be used to successfully extract Topical Components (TCs) from a source text, which are required by a supervised feature-based AES model. In particular, results show that feature-based AES performance is comparable with either automatically or manually constructed TCs.
%U https://aclanthology.org/2021.bea-1.9/
%P 85-96
Markdown (Informal)
[Essay Quality Signals as Weak Supervision for Source-based Essay Scoring](https://aclanthology.org/2021.bea-1.9/) (Zhang & Litman, BEA 2021)
ACL