Few-Shot Document-Level Relation Extraction
We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo).
Code (1)
Tasks
Document-level Relation ExtractionDomain AdaptationFew-Shot LearningFew-Shot Relation ClassificationRelationRelation ClassificationRelation ExtractionSentenceSimilar Papers 제목 키워드 기반
GLiDRE: Generalist Lightweight model for Document-level Relation Extraction
Relation Extraction (RE) is a fundamental task in Natural Language Processing, and its document-level variant poses significant challenges, due to complex interactions between entities across sentences. While supervised …
Document-level Relation ExtractionDocument-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models
Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is com…
Document-level Relation ExtractionFew-Shot Learningnamed-entity-recognitionNamed Entity Recognition+2Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a su…
DenoisingRelationRetrievalText Generation+1DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations
Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data g…
In-Context LearningJoint Entity and Relation ExtractionRelationRelation Extraction+1Document-Level Zero-Shot Relation Extraction with Entity Side Information
Document-Level Zero-Shot Relation Extraction (DocZSRE) aims to predict unseen relation labels in text documents without prior training on specific relations. Existing approaches rely on Large Language Models (LLMs) to ge…
Relation Extraction