@inproceedings{huidong-etal-2024-generate,
title = "Generate-then-Revise: An Effective Synthetic Training Data Generation Framework For Event Detection Retrieval",
author = "Huidong, Du and
Hao, Sun and
Pengyuan, Liu and
Dong, Yu",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.78/",
pages = "1011--1022",
language = "eng",
abstract = "{\textquotedblleft}Large language models (LLMs) struggle with event detection (ED) due to the structured and vari-able number of events in the output. Existing supervised approaches rely on a large amount ofmanually annotated corpora, facing challenges in practice when event types are diverse and theannotated data is scarce. We propose Generate-then-Revise (GtR), a framework that leveragesLLMs in the opposite direction to address these challenges in ED. GtR utilizes an LLM to gen-erate high-quality training data in three stages, including a novel data revision step to minimizenoise in the synthetic data. The generated data is then used to train a smaller model for evalua-tion. Our approach demonstrates significant improvements on the low-resource ED. We furtheranalyze the generated data, highlighting the potential of synthetic data generation for enhancingED performance.Introduction{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huidong-etal-2024-generate">
<titleInfo>
<title>Generate-then-Revise: An Effective Synthetic Training Data Generation Framework For Event Detection Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Du</namePart>
<namePart type="family">Huidong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Pengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Dong</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 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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>“Large language models (LLMs) struggle with event detection (ED) due to the structured and vari-able number of events in the output. Existing supervised approaches rely on a large amount ofmanually annotated corpora, facing challenges in practice when event types are diverse and theannotated data is scarce. We propose Generate-then-Revise (GtR), a framework that leveragesLLMs in the opposite direction to address these challenges in ED. GtR utilizes an LLM to gen-erate high-quality training data in three stages, including a novel data revision step to minimizenoise in the synthetic data. The generated data is then used to train a smaller model for evalua-tion. Our approach demonstrates significant improvements on the low-resource ED. We furtheranalyze the generated data, highlighting the potential of synthetic data generation for enhancingED performance.Introduction”</abstract>
<identifier type="citekey">huidong-etal-2024-generate</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.78/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>1011</start>
<end>1022</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generate-then-Revise: An Effective Synthetic Training Data Generation Framework For Event Detection Retrieval
%A Huidong, Du
%A Hao, Sun
%A Pengyuan, Liu
%A Dong, Yu
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F huidong-etal-2024-generate
%X “Large language models (LLMs) struggle with event detection (ED) due to the structured and vari-able number of events in the output. Existing supervised approaches rely on a large amount ofmanually annotated corpora, facing challenges in practice when event types are diverse and theannotated data is scarce. We propose Generate-then-Revise (GtR), a framework that leveragesLLMs in the opposite direction to address these challenges in ED. GtR utilizes an LLM to gen-erate high-quality training data in three stages, including a novel data revision step to minimizenoise in the synthetic data. The generated data is then used to train a smaller model for evalua-tion. Our approach demonstrates significant improvements on the low-resource ED. We furtheranalyze the generated data, highlighting the potential of synthetic data generation for enhancingED performance.Introduction”
%U https://aclanthology.org/2024.ccl-1.78/
%P 1011-1022
Markdown (Informal)
[Generate-then-Revise: An Effective Synthetic Training Data Generation Framework For Event Detection Retrieval](https://aclanthology.org/2024.ccl-1.78/) (Huidong et al., CCL 2024)
ACL