# Learning Dual Retrieval Module for Semi-supervised Relation Extraction

arXiv: https://arxiv.org/abs/1902.07814 · HTML: https://mlsanity.com/paper/1902.07814/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2019.

## Built on by (most cited first, 12 of 12)

- [Curriculum-Meta Learning for Order-Robust Continual Relation Extraction](https://mlsanity.com/paper/2101.01926/) (2021)
- [Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction](https://mlsanity.com/paper/2109.06415/) (2021)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation](https://mlsanity.com/paper/2305.15872/) (2023)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [Generative Meta-Learning for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2305.01920/) (2023)
- [Semi-supervised Relation Extraction via Data Augmentation and Consistency-training](https://mlsanity.com/paper/2306.10153/) (2023)
- [A systematic review of relation extraction task since the emergence of Transformers](https://mlsanity.com/paper/2511.03610/) (2025)
- [A Review on Semi-Supervised Relation Extraction](https://mlsanity.com/paper/2103.07575/) (2021)
- [From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction](https://mlsanity.com/paper/2112.01048/) (2021)
- [Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction](https://mlsanity.com/paper/2211.06014/) (2022)
- [Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge](https://mlsanity.com/paper/2601.10485/) (2026)

## Abstract (arXiv)

Relation extraction is an important task in structuring content of text data, and becomes especially challenging when learning with weak supervision---where only a limited number of labeled sentences are given and a large number of unlabeled sentences are available. Most existing work exploits unlabeled data based on the ideas of self-training (i.e., bootstrapping a model) and multi-view learning (e.g., ensembling multiple model variants). However, these methods either suffer from the issue of semantic drift, or do not fully capture the problem characteristics of relation extraction. In this paper, we leverage a key insight that retrieving sentences expressing a relation is a dual task of predicting relation label for a given sentence---two tasks are complementary to each other and can be optimized jointly for mutual enhancement. To model this intuition, we propose DualRE, a principled framework that introduces a retrieval module which is jointly trained with the original relation prediction module. In this way, high-quality samples selected by retrieval module from unlabeled data can be used to improve prediction module, and vice versa. Experimental resultsfootnotesmall Code and data can be found at urlhttps://github.com/INK-USC/DualRE. on two public datasets as well as case studies demonstrate the effectiveness of the DualRE approach.