# NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction

arXiv: https://arxiv.org/abs/1909.02177 · HTML: https://mlsanity.com/paper/1909.02177/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 24 of 24)

- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [WRENCH: A Comprehensive Benchmark for Weak Supervision](https://mlsanity.com/paper/2109.11377/) (2021)
- [A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2101.10213/) (2021)
- [Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance](https://mlsanity.com/paper/2311.01108/) (2023)
- [SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction](https://mlsanity.com/paper/2109.12093/) (2021)
- [A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing](https://mlsanity.com/paper/2209.13136/) (2022)
- [Creating Training Sets via Weak Indirect Supervision](https://mlsanity.com/paper/2110.03484/) (2021)
- [PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning](https://mlsanity.com/paper/2203.09735/) (2022)
- [Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning](https://mlsanity.com/paper/2205.02355/) (2022)
- [Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance](https://mlsanity.com/paper/2504.02901/) (2025)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling](https://mlsanity.com/paper/2305.19395/) (2023)
- [Meta Self-Refinement for Robust Learning with Weak Supervision](https://mlsanity.com/paper/2205.07290/) (2022)
- [Can Large Language Models Design Accurate Label Functions?](https://mlsanity.com/paper/2311.00739/) (2023)
- [Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2109.02099/) (2021)
- [It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers](https://mlsanity.com/paper/2204.11424/) (2022)
- [Pareto Optimal Learning for Estimating Large Language Model Errors](https://mlsanity.com/paper/2306.16564/) (2023)
- [Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction](https://mlsanity.com/paper/2206.13749/) (2022)
- [Binary Classification with Positive Labeling Sources](https://mlsanity.com/paper/2208.01704/) (2022)
- [Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation](https://mlsanity.com/paper/2404.04445/) (2024)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [Label Augmentation with Reinforced Labeling for Weak Supervision](https://mlsanity.com/paper/2204.06436/) (2022)
- [Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers](https://mlsanity.com/paper/2101.07138/) (2021)
- [From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction](https://mlsanity.com/paper/2112.01048/) (2021)

## Abstract (arXiv)

Deep neural models for relation extraction tend to be less reliable when perfectly labeled data is limited, despite their success in label-sufficient scenarios. Instead of seeking more instance-level labels from human annotators, here we propose to annotate frequent surface patterns to form labeling rules. These rules can be automatically mined from large text corpora and generalized via a soft rule matching mechanism. Prior works use labeling rules in an exact matching fashion, which inherently limits the coverage of sentence matching and results in the low-recall issue. In this paper, we present a neural approach to ground rules for RE, named NERO, which jointly learns a relation extraction module and a soft matching module. One can employ any neural relation extraction models as the instantiation for the RE module. The soft matching module learns to match rules with semantically similar sentences such that raw corpora can be automatically labeled and leveraged by the RE module (in a much better coverage) as augmented supervision, in addition to the exactly matched sentences. Extensive experiments and analysis on two public and widely-used datasets demonstrate the effectiveness of the proposed NERO framework, comparing with both rule-based and semi-supervised methods. Through user studies, we find that the time efficiency for a human to annotate rules and sentences are similar (0.30 vs. 0.35 min per label). In particular, NERO's performance using 270 rules is comparable to the models trained using 3,000 labeled sentences, yielding a 9.5x speedup. Moreover, NERO can predict for unseen relations at test time and provide interpretable predictions. We release our code to the community for future research.