PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programming

Chufan Gao, Xulin Fan, Jimeng Sun, Xuan Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Relation extraction aims to classify the relationships between two entities into pre-defined categories. While previous research has mainly focused on sentence-level relation extraction, recent studies have expanded the scope to document-level relation extraction. Traditional relation extraction methods heavily rely on human-annotated training data, which is time-consuming and labor-intensive. To mitigate the need for manual annotation, recent weakly-supervised approaches have been developed for sentence-level relation extraction while limited work has been done on document-level relation extraction. Weakly-supervised document-level relation extraction faces significant challenges due to an imbalanced number "no relation" instances and the failure of directly probing pretrained large language models for document relation extraction. To address these challenges, we propose PromptRE, a novel weakly-supervised document-level relation extraction method that combines prompting-based techniques with data programming. Furthermore, PromptRE incorporates the label distribution and entity types as prior knowledge to improve the performance. By leveraging the strengths of both prompting and data programming, PromptRE achieves improved performance in relation classification and effectively handles the "no relation" problem. Experimental results on ReDocRED, a benchmark dataset for document-level relation extraction, demonstrate the superiority of PromptRE over baseline approaches.

Original languageEnglish (US)
Title of host publicationKnowLLM 2024 - 1st Workshop on Towards Knowledgeable Language Models, Proceedings of the Workshop
EditorsSha Li, Manling Li, Michael J.Q. Zhang, Eunsol Choi, Mor Geva, Peter Hase, Heng Ji
PublisherAssociation for Computational Linguistics (ACL)
Pages132-145
Number of pages14
ISBN (Electronic)9798891761544
DOIs
StatePublished - 2024
Event1st Workshop on Towards Knowledgeable Language Models, KnowLLM 2024 - Co-located with ACL 2024 - Bangkok, Thailand
Duration: Aug 16 2024 → …

Publication series

NameKnowLLM 2024 - 1st Workshop on Towards Knowledgeable Language Models, Proceedings of the Workshop

Conference

Conference1st Workshop on Towards Knowledgeable Language Models, KnowLLM 2024 - Co-located with ACL 2024
Country/TerritoryThailand
CityBangkok
Period8/16/24 → …

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programming'. Together they form a unique fingerprint.

Cite this