# Reinforcement Learning for Relation Classification from Noisy Data

arXiv: https://arxiv.org/abs/1808.08013 · HTML: https://mlsanity.com/paper/1808.08013/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2018.

## Built on by (most cited first, 30 of 46)

- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.00327/) (2021)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks](https://mlsanity.com/paper/2104.07886/) (2021)
- [Prototypical Representation Learning for Relation Extraction](https://mlsanity.com/paper/2103.11647/) (2021)
- [Visual Distant Supervision for Scene Graph Generation](https://mlsanity.com/paper/2103.15365/) (2021)
- [Discriminative Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01562/) (2021)
- [SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction](https://mlsanity.com/paper/2109.12093/) (2021)
- [Revisiting the Negative Data of Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2105.10158/) (2021)
- [Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2105.09543/) (2021)
- [Relational Representation Learning in Visually-Rich Documents](https://mlsanity.com/paper/2205.02411/) (2022)
- [SENT: Sentence-level Distant Relation Extraction via Negative Training](https://mlsanity.com/paper/2106.11566/) (2021)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [Reinforcement Learning based Collective Entity Alignment with Adaptive Features](https://mlsanity.com/paper/2101.01353/) (2021)
- [Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification](https://mlsanity.com/paper/2101.03526/) (2021)
- [Towards Better Document-level Relation Extraction via Iterative Inference](https://mlsanity.com/paper/2211.14470/) (2022)
- [Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction](https://mlsanity.com/paper/2305.11029/) (2023)
- [Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation](https://mlsanity.com/paper/2206.08088/) (2022)
- [A Question-answering Based Framework for Relation Extraction Validation](https://mlsanity.com/paper/2104.02934/) (2021)
- [CorefDRE: Document-level Relation Extraction with coreference resolution](https://mlsanity.com/paper/2202.10744/) (2022)
- [Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization](https://mlsanity.com/paper/2504.05224/) (2025)
- [Learning to Selectively Learn for Weakly-supervised Paraphrase Generation](https://mlsanity.com/paper/2109.12457/) (2021)
- [Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning](https://mlsanity.com/paper/2111.06103/) (2021)
- [Improving Distantly Supervised Relation Extraction by Natural Language Inference](https://mlsanity.com/paper/2208.00346/) (2022)
- [RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm](https://mlsanity.com/paper/2301.02807/) (2023)
- [Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data](https://mlsanity.com/paper/2306.09697/) (2023)
- [Distantly-Supervised Joint Extraction with Noise-Robust Learning](https://mlsanity.com/paper/2310.04994/) (2023)
- [REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking](https://mlsanity.com/paper/2404.12788/) (2024)
- [Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels](https://mlsanity.com/paper/2406.16293/) (2024)

## Abstract (arXiv)

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffers from the noisy labeling problem. In this paper, we propose a novel model for relation classification at the sentence level from noisy data. The model has two modules: an instance selector and a relation classifier. The instance selector chooses high-quality sentences with reinforcement learning and feeds the selected sentences into the relation classifier, and the relation classifier makes sentence level prediction and provides rewards to the instance selector. The two modules are trained jointly to optimize the instance selection and relation classification processes. Experiment results show that our model can deal with the noise of data effectively and obtains better performance for relation classification at the sentence level.