@inproceedings{litao-etal-2024-multi,
title = "Multi-Model Classical {C}hinese Event Trigger Word Recognition Driven by Incremental Pre-training",
author = "Litao, Lin and
Mengcheng, Wu and
Xueying, Shen and
Jiaxin, Zhou and
Shiyan, Ou",
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-3.20/",
pages = "178--190",
language = "eng",
abstract = "{\textquotedblleft}This paper addresses the task of identifying and classifying historical event trigger words in Classical Chinese, utilizing both small-scale and large-scale language models. Specifically, we selected the small-scale language model GujiBERT for intelligent processing of classical texts, and the large-scale language model Xunzi-Qwen-14b. Both models underwent continued pretraining and fine-tuning, resulting in GujiBERT-CHED-mlm and Xunzi-Qwen-14b-CHED. For the small-scale language model, we used a BiLSTM as the feature extraction module and a CRF as the decoding module, employing a sequence labeling paradigm to complete the evaluation experiments. For the large-scale language model, we optimized the prompt templates and used a sequence-to-sequence paradigm for evaluation experiments. Our experiments revealed that GujiBERT-BiLSTM-CRF achieved the best performance across all tasks, ranking fourth in overall performance among all participating teams. The large-scale language model demonstrated good semantic understanding abilities, reaching a preliminary usable level. Future research should focus on enhancing its ability to produce standardized outputs.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="litao-etal-2024-multi">
<titleInfo>
<title>Multi-Model Classical Chinese Event Trigger Word Recognition Driven by Incremental Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Litao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wu</namePart>
<namePart type="family">Mengcheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shen</namePart>
<namePart type="family">Xueying</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Jiaxin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ou</namePart>
<namePart type="family">Shiyan</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>“This paper addresses the task of identifying and classifying historical event trigger words in Classical Chinese, utilizing both small-scale and large-scale language models. Specifically, we selected the small-scale language model GujiBERT for intelligent processing of classical texts, and the large-scale language model Xunzi-Qwen-14b. Both models underwent continued pretraining and fine-tuning, resulting in GujiBERT-CHED-mlm and Xunzi-Qwen-14b-CHED. For the small-scale language model, we used a BiLSTM as the feature extraction module and a CRF as the decoding module, employing a sequence labeling paradigm to complete the evaluation experiments. For the large-scale language model, we optimized the prompt templates and used a sequence-to-sequence paradigm for evaluation experiments. Our experiments revealed that GujiBERT-BiLSTM-CRF achieved the best performance across all tasks, ranking fourth in overall performance among all participating teams. The large-scale language model demonstrated good semantic understanding abilities, reaching a preliminary usable level. Future research should focus on enhancing its ability to produce standardized outputs.”</abstract>
<identifier type="citekey">litao-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-3.20/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>178</start>
<end>190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Model Classical Chinese Event Trigger Word Recognition Driven by Incremental Pre-training
%A Litao, Lin
%A Mengcheng, Wu
%A Xueying, Shen
%A Jiaxin, Zhou
%A Shiyan, Ou
%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 litao-etal-2024-multi
%X “This paper addresses the task of identifying and classifying historical event trigger words in Classical Chinese, utilizing both small-scale and large-scale language models. Specifically, we selected the small-scale language model GujiBERT for intelligent processing of classical texts, and the large-scale language model Xunzi-Qwen-14b. Both models underwent continued pretraining and fine-tuning, resulting in GujiBERT-CHED-mlm and Xunzi-Qwen-14b-CHED. For the small-scale language model, we used a BiLSTM as the feature extraction module and a CRF as the decoding module, employing a sequence labeling paradigm to complete the evaluation experiments. For the large-scale language model, we optimized the prompt templates and used a sequence-to-sequence paradigm for evaluation experiments. Our experiments revealed that GujiBERT-BiLSTM-CRF achieved the best performance across all tasks, ranking fourth in overall performance among all participating teams. The large-scale language model demonstrated good semantic understanding abilities, reaching a preliminary usable level. Future research should focus on enhancing its ability to produce standardized outputs.”
%U https://aclanthology.org/2024.ccl-3.20/
%P 178-190
Markdown (Informal)
[Multi-Model Classical Chinese Event Trigger Word Recognition Driven by Incremental Pre-training](https://aclanthology.org/2024.ccl-3.20/) (Litao et al., CCL 2024)
ACL