# Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction

arXiv: https://arxiv.org/abs/2011.13574 · HTML: https://mlsanity.com/paper/2011.13574/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion](https://mlsanity.com/paper/2108.01387/) (2021)
- [All-around Neural Collapse for Imbalanced Classification](https://mlsanity.com/paper/2408.07253/) (2024)
- [Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique Identifier](https://mlsanity.com/paper/2501.05155/) (2025)
- [SememeLM: A Sememe Knowledge Enhanced Method for Long-tail Relation Representation](https://mlsanity.com/paper/2406.10297/) (2024)
- [Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning](https://mlsanity.com/paper/2603.15708/) (2026)
- [Information Density Imbalance in Visual Object Detection](https://mlsanity.com/paper/2609.02369/) (2026)

## Abstract (arXiv)

Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts.However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lackof sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well as theirproximities for transfer learning. Specifically, we construct a co-occurrence graph from texts, and capture both first-order andsecond-order entity proximities for embedding learning. Based on this, we further optimize the distance from entity pairs tocorresponding prototypes, which can be easily adapted to almost arbitrary RE frameworks. Thus, the learning of infrequent or evenunseen relation types will benefit from semantically proximate relations through pairs of entities and large-scale textual information.We have conducted extensive experiments on two publicly available datasets: New York Times and Google Distant Supervision.Compared with eight state-of-the-art baselines, our proposed model achieves significant improvements (4.1% F1 on average). Furtherresults on long-tail relations demonstrate the effectiveness of the learned relation prototypes. We further conduct an ablation study toinvestigate the impacts of varying components, and apply it to four basic relation extraction models to verify the generalization ability.Finally, we analyze several example cases to give intuitive impressions as qualitative analysis. Our codes will be released later.