@inproceedings{ding-etal-2020-chinese,
title = "{C}hinese Content Scoring: Open-Access Datasets and Features on Different Segmentation Levels",
author = "Ding, Yuning and
Horbach, Andrea and
Zesch, Torsten",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.37/",
doi = "10.18653/v1/2020.aacl-main.37",
pages = "347--357",
abstract = "In this paper, we analyse the challenges of Chinese content scoring in comparison to English. As a review of prior work for Chinese content scoring shows a lack of open-access data in the field, we present two short-answer data sets for Chinese. The Chinese Educational Short Answers data set (CESA) contains 1800 student answers for five science-related questions. As a second data set, we collected ASAP-ZH with 942 answers by re-using three existing prompts from the ASAP data set. We adapt a state-of-the-art content scoring system for Chinese and evaluate it in several settings on these data sets. Results show that features on lower segmentation levels such as character n-grams tend to have better performance than features on token level."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2020-chinese">
<titleInfo>
<title>Chinese Content Scoring: Open-Access Datasets and Features on Different Segmentation Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuning</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we analyse the challenges of Chinese content scoring in comparison to English. As a review of prior work for Chinese content scoring shows a lack of open-access data in the field, we present two short-answer data sets for Chinese. The Chinese Educational Short Answers data set (CESA) contains 1800 student answers for five science-related questions. As a second data set, we collected ASAP-ZH with 942 answers by re-using three existing prompts from the ASAP data set. We adapt a state-of-the-art content scoring system for Chinese and evaluate it in several settings on these data sets. Results show that features on lower segmentation levels such as character n-grams tend to have better performance than features on token level.</abstract>
<identifier type="citekey">ding-etal-2020-chinese</identifier>
<identifier type="doi">10.18653/v1/2020.aacl-main.37</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.37/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>347</start>
<end>357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese Content Scoring: Open-Access Datasets and Features on Different Segmentation Levels
%A Ding, Yuning
%A Horbach, Andrea
%A Zesch, Torsten
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F ding-etal-2020-chinese
%X In this paper, we analyse the challenges of Chinese content scoring in comparison to English. As a review of prior work for Chinese content scoring shows a lack of open-access data in the field, we present two short-answer data sets for Chinese. The Chinese Educational Short Answers data set (CESA) contains 1800 student answers for five science-related questions. As a second data set, we collected ASAP-ZH with 942 answers by re-using three existing prompts from the ASAP data set. We adapt a state-of-the-art content scoring system for Chinese and evaluate it in several settings on these data sets. Results show that features on lower segmentation levels such as character n-grams tend to have better performance than features on token level.
%R 10.18653/v1/2020.aacl-main.37
%U https://aclanthology.org/2020.aacl-main.37/
%U https://doi.org/10.18653/v1/2020.aacl-main.37
%P 347-357
Markdown (Informal)
[Chinese Content Scoring: Open-Access Datasets and Features on Different Segmentation Levels](https://aclanthology.org/2020.aacl-main.37/) (Ding et al., AACL 2020)
ACL