# PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detection

arXiv: https://arxiv.org/abs/2211.14477 · HTML: https://mlsanity.com/paper/2211.14477/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 26 Nov 2022.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders](https://mlsanity.com/paper/2010.03851/) (2020)
- [TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking](https://mlsanity.com/paper/2010.13415/) (2020)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Joint Entity and Relation Extraction with Set Prediction Networks](https://mlsanity.com/paper/2011.01675/) (2020)
- [A Hierarchical Framework for Relation Extraction with Reinforcement Learning](https://mlsanity.com/paper/1811.03925/) (2018)
- [ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning](https://mlsanity.com/paper/2104.04697/) (2021)
- [PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction](https://mlsanity.com/paper/2106.09895/) (2021)
- [Question Answering on Freebase via Relation Extraction and Textual Evidence](https://mlsanity.com/paper/1603.00957/) (2016)
- [OneRel:Joint Entity and Relation Extraction with One Module in One Step](https://mlsanity.com/paper/2203.05412/) (2022)
- [A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling](https://mlsanity.com/paper/2109.06705/) (2021)

## Built on by (most cited first, 2 of 2)

- [Generative Meta-Learning for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2305.01920/) (2023)
- [MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning](https://mlsanity.com/paper/2601.12680/) (2026)

## Abstract (arXiv)

Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts under the zero-shot setting, where the relation sets at the training and testing stages are disjoint. Previous state-of-the-art method handles this challenging task by leveraging pretrained language models to generate data as additional training samples, which increases the training cost and severely constrains the model performance. To address the above issues, we propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation Selection and Entity Boundary Detection. The remarkable characteristic of PCRED is that it does not rely on additional data and still achieves promising performance. The model adopts a relation-first paradigm, recognizing unseen relations through candidate relation selection. With this approach, the semantics of relations are naturally infused in the context. Entities are extracted based on the context and the semantics of relations subsequently. We evaluate our model on two ZeroRTE datasets. The experiment results show that our method consistently outperforms previous works. Our code will be available at https://anonymous.4open.science/r/PCRED.