@inproceedings{saini-nayak-2025-effective,
title = "Effective Modeling of Generative Framework for Document-level Relational Triple Extraction",
author = "Saini, Pratik and
Nayak, Tapas",
editor = "Gesese, Genet Asefa and
Sack, Harald and
Paulheim, Heiko and
Merono-Penuela, Albert and
Chen, Lihu",
booktitle = "Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.genaik-1.1/",
pages = "1--12",
abstract = "Document-level relation triple extraction (DocRTE) is a complex task that involves three key sub-tasks: entity mention extraction, entity clustering, and relation triple extraction. Past work has applied discriminative models to address these three sub-tasks, either by training them sequentially in a pipeline fashion or jointly training them. However, while end-to-end discriminative or generative models have proven effective for sentence-level relation triple extraction, they cannot be trivially extended to the document level, as they only handle relation extraction without addressing the remaining two sub-tasks, entity mention extraction or clustering. In this paper, we propose a three-stage generative framework leveraging a pre-trained BART model to address all three tasks required for document-level relation triple extraction. Tested on the widely used DocRED dataset, our approach outperforms previous generative methods and achieves competitive performance against discriminative models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saini-nayak-2025-effective">
<titleInfo>
<title>Effective Modeling of Generative Framework for Document-level Relational Triple Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Saini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tapas</namePart>
<namePart type="family">Nayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Genet</namePart>
<namePart type="given">Asefa</namePart>
<namePart type="family">Gesese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Sack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heiko</namePart>
<namePart type="family">Paulheim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Merono-Penuela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-level relation triple extraction (DocRTE) is a complex task that involves three key sub-tasks: entity mention extraction, entity clustering, and relation triple extraction. Past work has applied discriminative models to address these three sub-tasks, either by training them sequentially in a pipeline fashion or jointly training them. However, while end-to-end discriminative or generative models have proven effective for sentence-level relation triple extraction, they cannot be trivially extended to the document level, as they only handle relation extraction without addressing the remaining two sub-tasks, entity mention extraction or clustering. In this paper, we propose a three-stage generative framework leveraging a pre-trained BART model to address all three tasks required for document-level relation triple extraction. Tested on the widely used DocRED dataset, our approach outperforms previous generative methods and achieves competitive performance against discriminative models.</abstract>
<identifier type="citekey">saini-nayak-2025-effective</identifier>
<location>
<url>https://aclanthology.org/2025.genaik-1.1/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Modeling of Generative Framework for Document-level Relational Triple Extraction
%A Saini, Pratik
%A Nayak, Tapas
%Y Gesese, Genet Asefa
%Y Sack, Harald
%Y Paulheim, Heiko
%Y Merono-Penuela, Albert
%Y Chen, Lihu
%S Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F saini-nayak-2025-effective
%X Document-level relation triple extraction (DocRTE) is a complex task that involves three key sub-tasks: entity mention extraction, entity clustering, and relation triple extraction. Past work has applied discriminative models to address these three sub-tasks, either by training them sequentially in a pipeline fashion or jointly training them. However, while end-to-end discriminative or generative models have proven effective for sentence-level relation triple extraction, they cannot be trivially extended to the document level, as they only handle relation extraction without addressing the remaining two sub-tasks, entity mention extraction or clustering. In this paper, we propose a three-stage generative framework leveraging a pre-trained BART model to address all three tasks required for document-level relation triple extraction. Tested on the widely used DocRED dataset, our approach outperforms previous generative methods and achieves competitive performance against discriminative models.
%U https://aclanthology.org/2025.genaik-1.1/
%P 1-12
Markdown (Informal)
[Effective Modeling of Generative Framework for Document-level Relational Triple Extraction](https://aclanthology.org/2025.genaik-1.1/) (Saini & Nayak, GenAIK 2025)
ACL