@inproceedings{jinwang-etal-2024-essay,
title = "Essay Rhetoric Recognition and Understanding Using Synthetic Data and Model Ensemble Enhanced Large Language Models",
author = "Jinwang, Song and
Hongying, Zan and
Kunli, Zhang",
editor = "Lin, Hongfei and
Tan, Hongye and
Li, Bin",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-3.25/",
pages = "223--231",
language = "eng",
abstract = "{\textquotedblleft}Natural language processing technology has been widely applied in the field of education. Essay writing serves as a crucial method for evaluating students' language skills and logical thinking abilities. Rhetoric, an essential component of essay, is also a key reference for assessing writing quality. In the era of large language models (LLMs), applying LLMs to the tasks of automatic classification and extraction of rhetorical devices is of significant importance. In this paper, we fine-tune LLMs with specific instructions to adapt them for the tasks of recognizing and extracting rhetorical devices in essays. To further enhance the performance of LLMs, we experimented with multi-task fine-tuning and expanded the training dataset through synthetic data. Additionally, we explored a model ensemble approach based on label re-inference. Our method achieved a score of 66.29 in Task 6 of the CCL 2024 Eval, Chinese Essay Rhetoric Recognition and Understanding(CERRU), securing the first position.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jinwang-etal-2024-essay">
<titleInfo>
<title>Essay Rhetoric Recognition and Understanding Using Synthetic Data and Model Ensemble Enhanced Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Jinwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zan</namePart>
<namePart type="family">Hongying</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Kunli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongye</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Natural language processing technology has been widely applied in the field of education. Essay writing serves as a crucial method for evaluating students’ language skills and logical thinking abilities. Rhetoric, an essential component of essay, is also a key reference for assessing writing quality. In the era of large language models (LLMs), applying LLMs to the tasks of automatic classification and extraction of rhetorical devices is of significant importance. In this paper, we fine-tune LLMs with specific instructions to adapt them for the tasks of recognizing and extracting rhetorical devices in essays. To further enhance the performance of LLMs, we experimented with multi-task fine-tuning and expanded the training dataset through synthetic data. Additionally, we explored a model ensemble approach based on label re-inference. Our method achieved a score of 66.29 in Task 6 of the CCL 2024 Eval, Chinese Essay Rhetoric Recognition and Understanding(CERRU), securing the first position.”</abstract>
<identifier type="citekey">jinwang-etal-2024-essay</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-3.25/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>223</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Essay Rhetoric Recognition and Understanding Using Synthetic Data and Model Ensemble Enhanced Large Language Models
%A Jinwang, Song
%A Hongying, Zan
%A Kunli, Zhang
%Y Lin, Hongfei
%Y Tan, Hongye
%Y Li, Bin
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F jinwang-etal-2024-essay
%X “Natural language processing technology has been widely applied in the field of education. Essay writing serves as a crucial method for evaluating students’ language skills and logical thinking abilities. Rhetoric, an essential component of essay, is also a key reference for assessing writing quality. In the era of large language models (LLMs), applying LLMs to the tasks of automatic classification and extraction of rhetorical devices is of significant importance. In this paper, we fine-tune LLMs with specific instructions to adapt them for the tasks of recognizing and extracting rhetorical devices in essays. To further enhance the performance of LLMs, we experimented with multi-task fine-tuning and expanded the training dataset through synthetic data. Additionally, we explored a model ensemble approach based on label re-inference. Our method achieved a score of 66.29 in Task 6 of the CCL 2024 Eval, Chinese Essay Rhetoric Recognition and Understanding(CERRU), securing the first position.”
%U https://aclanthology.org/2024.ccl-3.25/
%P 223-231
Markdown (Informal)
[Essay Rhetoric Recognition and Understanding Using Synthetic Data and Model Ensemble Enhanced Large Language Models](https://aclanthology.org/2024.ccl-3.25/) (Jinwang et al., CCL 2024)
ACL