# Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

arXiv: https://arxiv.org/abs/2104.08481 · HTML: https://mlsanity.com/paper/2104.08481/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [Graph Convolution over Pruned Dependency Trees Improves Relation Extraction](https://mlsanity.com/paper/1809.10185/) (2018)
- [Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning](https://mlsanity.com/paper/1903.12290/) (2019)
- [FewRel 2.0: Towards More Challenging Few-Shot Relation Classification](https://mlsanity.com/paper/1910.07124/) (2019)
- [Diverse Few-Shot Text Classification with Multiple Metrics](https://mlsanity.com/paper/1805.07513/) (2018)
- [Few-shot Text Classification with Distributional Signatures](https://mlsanity.com/paper/1908.06039/) (2019)
- [Out-of-Domain Detection for Low-Resource Text Classification Tasks](https://mlsanity.com/paper/1909.05357/) (2019)

## Built on by (most cited first, 27 of 27)

- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [CrossRE: A Cross-Domain Dataset for Relation Extraction](https://mlsanity.com/paper/2210.09345/) (2022)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [GLiREL -- Generalist Model for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2501.03172/) (2025)
- [Few-Shot Document-Level Relation Extraction](https://mlsanity.com/paper/2205.02048/) (2022)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [A Dataset for N-ary Relation Extraction of Drug Combinations](https://mlsanity.com/paper/2205.02289/) (2022)
- [Few-Shot Document-Level Event Argument Extraction](https://mlsanity.com/paper/2209.02203/) (2022)
- [Benchmarking Long-tail Generalization with Likelihood Splits](https://mlsanity.com/paper/2210.06799/) (2022)
- [RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction](https://mlsanity.com/paper/2310.15743/) (2023)
- [Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification](https://mlsanity.com/paper/2403.03305/) (2024)
- [AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities](https://mlsanity.com/paper/2203.05325/) (2022)
- [Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study](https://mlsanity.com/paper/2210.10678/) (2022)
- [Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction](https://mlsanity.com/paper/2305.10985/) (2023)
- [From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction](https://mlsanity.com/paper/2202.00475/) (2022)
- [GLiDRE: Generalist Lightweight model for Document-level Relation Extraction](https://mlsanity.com/paper/2508.00757/) (2025)
- [CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation](https://mlsanity.com/paper/2310.12024/) (2023)
- [Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation](https://mlsanity.com/paper/2404.04445/) (2024)
- [P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization](https://mlsanity.com/paper/2202.07615/) (2022)
- [TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extraction](https://mlsanity.com/paper/2410.00412/) (2024)
- [Diversity Over Quantity: A Lesson From Few Shot Relation Classification](https://mlsanity.com/paper/2412.05434/) (2024)
- [A systematic review of relation extraction task since the emergence of Transformers](https://mlsanity.com/paper/2511.03610/) (2025)
- [Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction](https://mlsanity.com/paper/2601.20803/) (2026)
- [A Few-Shot Learning Focused Survey on Recent Named Entity Recognition and Relation Classification Methods](https://mlsanity.com/paper/2310.19055/) (2023)
- [Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents](https://mlsanity.com/paper/2403.15765/) (2024)
- [A Study on Building Efficient Zero-Shot Relation Extraction Models](https://mlsanity.com/paper/2603.01266/) (2026)
- [Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement](https://mlsanity.com/paper/2606.29639/) (2026)

## Abstract (arXiv)

We explore Few-Shot Learning (FSL) for Relation Classification (RC). Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, aka NOTA), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution. To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. This yields a new challenging benchmark for FSL RC, on which state of the art models show poor performance. Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space. Triggered by this analysis we propose a novel classification scheme, in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.