@inproceedings{shen-etal-2024-towards,
title = "Towards Explainable {C}hinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method",
author = "Shen, Xinshu and
Wu, Hongyi and
Zhang, Yadong and
Lan, Man and
Bai, Xiaopeng and
Mao, Shaoguang and
Wu, Yuanbin and
Zhuang, Xinlin and
Cai, Li",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.910",
pages = "15515--15528",
abstract = "Grammatical Error Correction (GEC) is a crucial technique in Automated Essay Scoring (AES) for evaluating the fluency of essays. However, in Chinese, existing GEC datasets often fail to consider the importance of specific grammatical error types within compositional scenarios, lack research on data collected from native Chinese speakers, and largely overlook cross-sentence grammatical errors. Furthermore, the measurement of the overall fluency of an essay is often overlooked. To address these issues, we present CEFA (Chinese Essay Fluency Assessment), an extensive corpus that is derived from essays authored by native Chinese-speaking primary and secondary students and encapsulates essay fluency scores along with both coarse and fine-grained grammatical error types and corrections. Experiments employing various benchmark models on CEFA substantiate the challenge of our dataset. Our findings further highlight the significance of fine-grained annotations in fluency assessment and the mutually beneficial relationship between error types and corrections",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2024-towards">
<titleInfo>
<title>Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinshu</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Man</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaopeng</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoguang</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanbin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlin</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical Error Correction (GEC) is a crucial technique in Automated Essay Scoring (AES) for evaluating the fluency of essays. However, in Chinese, existing GEC datasets often fail to consider the importance of specific grammatical error types within compositional scenarios, lack research on data collected from native Chinese speakers, and largely overlook cross-sentence grammatical errors. Furthermore, the measurement of the overall fluency of an essay is often overlooked. To address these issues, we present CEFA (Chinese Essay Fluency Assessment), an extensive corpus that is derived from essays authored by native Chinese-speaking primary and secondary students and encapsulates essay fluency scores along with both coarse and fine-grained grammatical error types and corrections. Experiments employing various benchmark models on CEFA substantiate the challenge of our dataset. Our findings further highlight the significance of fine-grained annotations in fluency assessment and the mutually beneficial relationship between error types and corrections</abstract>
<identifier type="citekey">shen-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.910</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15515</start>
<end>15528</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method
%A Shen, Xinshu
%A Wu, Hongyi
%A Zhang, Yadong
%A Lan, Man
%A Bai, Xiaopeng
%A Mao, Shaoguang
%A Wu, Yuanbin
%A Zhuang, Xinlin
%A Cai, Li
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F shen-etal-2024-towards
%X Grammatical Error Correction (GEC) is a crucial technique in Automated Essay Scoring (AES) for evaluating the fluency of essays. However, in Chinese, existing GEC datasets often fail to consider the importance of specific grammatical error types within compositional scenarios, lack research on data collected from native Chinese speakers, and largely overlook cross-sentence grammatical errors. Furthermore, the measurement of the overall fluency of an essay is often overlooked. To address these issues, we present CEFA (Chinese Essay Fluency Assessment), an extensive corpus that is derived from essays authored by native Chinese-speaking primary and secondary students and encapsulates essay fluency scores along with both coarse and fine-grained grammatical error types and corrections. Experiments employing various benchmark models on CEFA substantiate the challenge of our dataset. Our findings further highlight the significance of fine-grained annotations in fluency assessment and the mutually beneficial relationship between error types and corrections
%U https://aclanthology.org/2024.findings-emnlp.910
%P 15515-15528
Markdown (Informal)
[Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method](https://aclanthology.org/2024.findings-emnlp.910) (Shen et al., Findings 2024)
ACL
- Xinshu Shen, Hongyi Wu, Yadong Zhang, Man Lan, Xiaopeng Bai, Shaoguang Mao, Yuanbin Wu, Xinlin Zhuang, and Li Cai. 2024. Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15515–15528, Miami, Florida, USA. Association for Computational Linguistics.