# Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data

arXiv: https://arxiv.org/abs/2306.09697 · HTML: https://mlsanity.com/paper/2306.09697/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 47 references that are in the map.
- First posted on arXiv 16 Jun 2023.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs](https://mlsanity.com/paper/1909.00228/) (2019)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Reinforcement Learning for Relation Classification from Noisy Data](https://mlsanity.com/paper/1808.08013/) (2018)
- [Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning](https://mlsanity.com/paper/1906.01378/) (2019)
- [Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction](https://mlsanity.com/paper/1802.10569/) (2018)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Aspect Term Extraction with History Attention and Selective Transformation](https://mlsanity.com/paper/1805.00760/) (2018)
- [Semi-supervised Relation Extraction via Incremental Meta Self-Training](https://mlsanity.com/paper/2010.16410/) (2020)
- [Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition](https://mlsanity.com/paper/2012.05426/) (2020)
- [Better Feature Integration for Named Entity Recognition](https://mlsanity.com/paper/2104.05316/) (2021)
- [Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion](https://mlsanity.com/paper/1909.11359/) (2019)
- [Denoising Relation Extraction from Document-level Distant Supervision](https://mlsanity.com/paper/2011.03888/) (2020)
- [Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED](https://mlsanity.com/paper/2204.07980/) (2022)
- [Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.00209/) (2021)
- [A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach](https://mlsanity.com/paper/2211.10018/) (2022)
- [A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes](https://mlsanity.com/paper/2204.06584/) (2022)

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

- [Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding](https://mlsanity.com/paper/2507.09758/) (2025)
- [VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction](https://mlsanity.com/paper/2412.13503/) (2024)

## Abstract (arXiv)

Relation extraction (RE) aims to extract relations from sentences and documents. Existing relation extraction models typically rely on supervised machine learning. However, recent studies showed that many RE datasets are incompletely annotated. This is known as the false negative problem in which valid relations are falsely annotated as 'no_relation'. Models trained with such data inevitably make similar mistakes during the inference stage. Self-training has been proven effective in alleviating the false negative problem. However, traditional self-training is vulnerable to confirmation bias and exhibits poor performance in minority classes. To overcome this limitation, we proposed a novel class-adaptive re-sampling self-training framework. Specifically, we re-sampled the pseudo-labels for each class by precision and recall scores. Our re-sampling strategy favored the pseudo-labels of classes with high precision and low recall, which improved the overall recall without significantly compromising precision. We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated. Our code is released at https://github.com/DAMO-NLP-SG/CAST.