# Unsupervised Relation Extraction from Language Models using Constrained Cloze Completion

arXiv: https://arxiv.org/abs/2010.06804 · HTML: https://mlsanity.com/paper/2010.06804/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Interpreting Language Models Through Knowledge Graph Extraction](https://mlsanity.com/paper/2111.08546/) (2021)
- [Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction](https://mlsanity.com/paper/2401.13598/) (2024)
- [Extracting Multi-valued Relations from Language Models](https://mlsanity.com/paper/2307.03122/) (2023)
- [On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction](https://mlsanity.com/paper/2402.18061/) (2024)
- [Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network](https://mlsanity.com/paper/2409.13621/) (2024)
- [Augmenting Task-Oriented Dialogue Systems with Relation Extraction](https://mlsanity.com/paper/2210.13344/) (2022)
- [Learning with Silver Standard Data for Zero-shot Relation Extraction](https://mlsanity.com/paper/2211.13883/) (2022)

## Abstract (arXiv)

We show that state-of-the-art self-supervised language models can be readily used to extract relations from a corpus without the need to train a fine-tuned extractive head. We introduce RE-Flex, a simple framework that performs constrained cloze completion over pretrained language models to perform unsupervised relation extraction. RE-Flex uses contextual matching to ensure that language model predictions matches supporting evidence from the input corpus that is relevant to a target relation. We perform an extensive experimental study over multiple relation extraction benchmarks and demonstrate that RE-Flex outperforms competing unsupervised relation extraction methods based on pretrained language models by up to 27.8 F1 points compared to the next-best method. Our results show that constrained inference queries against a language model can enable accurate unsupervised relation extraction.