@inproceedings{li-etal-2023-semi,
title = "Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models",
author = "Li, Junpeng and
Jia, Zixia and
Zheng, Zilong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.334",
doi = "10.18653/v1/2023.emnlp-main.334",
pages = "5495--5505",
abstract = "Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by recent advances in in-context learning capabilities emergent from large language models (LLMs), such as ChatGPT, we aim to design an automated annotation method for DocRE with minimum human effort. Unfortunately, vanilla in-context learning is infeasible for DocRE due to the plenty of predefined fine-grained relation types and the uncontrolled generations of LLMs. To tackle this issue, we propose a method integrating an LLM and a natural language inference (NLI) module to generate relation triples, thereby augmenting document-level relation datasets. We demonstrate the effectiveness of our approach by introducing an enhanced dataset known as DocGNRE, which excels in re-annotating numerous long-tail relation types. We are confident that our method holds the potential for broader applications in domain-specific relation type definitions and offers tangible benefits in advancing generalized language semantic comprehension.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-semi">
<titleInfo>
<title>Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junpeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixia</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by recent advances in in-context learning capabilities emergent from large language models (LLMs), such as ChatGPT, we aim to design an automated annotation method for DocRE with minimum human effort. Unfortunately, vanilla in-context learning is infeasible for DocRE due to the plenty of predefined fine-grained relation types and the uncontrolled generations of LLMs. To tackle this issue, we propose a method integrating an LLM and a natural language inference (NLI) module to generate relation triples, thereby augmenting document-level relation datasets. We demonstrate the effectiveness of our approach by introducing an enhanced dataset known as DocGNRE, which excels in re-annotating numerous long-tail relation types. We are confident that our method holds the potential for broader applications in domain-specific relation type definitions and offers tangible benefits in advancing generalized language semantic comprehension.</abstract>
<identifier type="citekey">li-etal-2023-semi</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.334</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.334</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5495</start>
<end>5505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
%A Li, Junpeng
%A Jia, Zixia
%A Zheng, Zilong
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-semi
%X Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by recent advances in in-context learning capabilities emergent from large language models (LLMs), such as ChatGPT, we aim to design an automated annotation method for DocRE with minimum human effort. Unfortunately, vanilla in-context learning is infeasible for DocRE due to the plenty of predefined fine-grained relation types and the uncontrolled generations of LLMs. To tackle this issue, we propose a method integrating an LLM and a natural language inference (NLI) module to generate relation triples, thereby augmenting document-level relation datasets. We demonstrate the effectiveness of our approach by introducing an enhanced dataset known as DocGNRE, which excels in re-annotating numerous long-tail relation types. We are confident that our method holds the potential for broader applications in domain-specific relation type definitions and offers tangible benefits in advancing generalized language semantic comprehension.
%R 10.18653/v1/2023.emnlp-main.334
%U https://aclanthology.org/2023.emnlp-main.334
%U https://doi.org/10.18653/v1/2023.emnlp-main.334
%P 5495-5505
Markdown (Informal)
[Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models](https://aclanthology.org/2023.emnlp-main.334) (Li et al., EMNLP 2023)
ACL