Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing

Few-Shot Relation Classification

3260 papers • 126 benchmarks • 313 datasets

Few-Shot Relation Classification is a particular relation classification task under minimum annotated data, where a model is required to classify a new incoming query instance given only few support instances (e.g., 1 or 5) during testing. Source: MICK: A Meta-Learning Framework for Few-shot Relation Classification with Little Training Data

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in few-shot-relation-classification

Trend

Dataset

Best Model

Actions

DocRED

DocRED

SciERC

SciERC

FREDo

FREDo

Libraries

i

Use these libraries to find few-shot-relation-classification models and implementations

Datasets

FewRel

DocRED

SciERC

FewRel 2.0

FREDo

TexRel

Subtasks

No subtasks available.

Most implemented papers

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

Xu Han, Zhiyuan Liu, Maosong Sun, Hao Zhu, Pengfei Yu, Ziyun Wang, Y. Yao•Tue Oct 23 2018

Empirical results show that even the most competitive few- shot learning models struggle on this task, especially as compared with humans, and indicate that few-shot relation classification remains an open problem and still requires further research.

671

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

FREDo (cross-domain)

FREDo (cross-domain)

0

Matching the Blanks: Distributional Similarity for Relation Learning

T. Kwiatkowski, Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling•Thu Jun 06 2019

This paper builds on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text.

838 0

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

Xu Han, Zhiyuan Liu, Maosong Sun, Tianyu Gao, Hao Zhu, Peng Li, Jie Zhou•Mon Sep 30 2019

It is found that the state-of-the-art few-shot relation classification models struggle on these two aspects, and that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well.

270 0

Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

Zhiquan Ye, Zhenhua Ling•Fri May 31 2019

A multi-level matching and aggregation network (MLMAN) for few-shot relation classification that encodes the query instance and each support set in an interactive way by considering their matching information at both local and instance levels.

144 0

Few-Shot Document-Level Relation Extraction

Michael Färber, Nicholas Popovic•Tue May 03 2022

This work adapts the state-of-the-art sentence-level method MNAV to the document-level and develops it further for improved domain adaptation and finds FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set.

18 0

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification

Xu Han, Zhiyuan Liu, Maosong Sun, Tianyu Gao, Ruobing Xie, Yuan Yao, Bowen Dong, Fen Lin, Leyu Lin•Mon Nov 30 2020

This work proposes a novel meta-information guided meta-learning (MIML) framework, where semantic concepts of classes provide strong guidance for meta- learning in both initialization and adaptation, which enables more effective initialization and faster adaptation.

44 0

CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation

Jochen De Weerdt, Philipp Borchert, Kristof Coussement, Arno De Caigny, Marie-Francine Moens•Tue Oct 17 2023

The information richness embedded in business entities allows models to focus on contextual nuances, reducing their reliance on superficial clues such as relation-specific verbs, which highlights the importance of high-quality data for robust domain adaptation.

3 0

Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning

Jochen De Weerdt, Philipp Borchert, Marie-Francine Moens•Sun Mar 24 2024

A novel approach to enhance information extraction combining multiple sentence representations and contrastive learning is introduced, validating the adaptability of the approach, maintaining robust performance in scenarios that include relation descriptions, and showcasing its flexibility to adapt to different resource constraints.

8 0

Adding a benchmark result helps the community track progress.

Few-Shot Relation Classification | State-of-the-Art