# None Class Ranking Loss for Document-Level Relation Extraction

arXiv: https://arxiv.org/abs/2205.00476 · HTML: https://mlsanity.com/paper/2205.00476/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 1 May 2022.

## Builds on (most cited first, 26 of 26)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [Graph Convolution over Pruned Dependency Trees Improves Relation Extraction](https://mlsanity.com/paper/1809.10185/) (2018)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Reasoning with Latent Structure Refinement for Document-Level Relation Extraction](https://mlsanity.com/paper/2005.06312/) (2020)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Coreferential Reasoning Learning for Language Representation](https://mlsanity.com/paper/2004.06870/) (2020)
- [Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs](https://mlsanity.com/paper/1909.00228/) (2019)
- [Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2004.08056/) (2020)
- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [Document-Level N-ary Relation Extraction with Multiscale Representation Learning](https://mlsanity.com/paper/1904.02347/) (2019)
- [Global-to-Local Neural Networks for Document-Level Relation Extraction](https://mlsanity.com/paper/2009.10359/) (2020)
- [HIN: Hierarchical Inference Network for Document-Level Relation Extraction](https://mlsanity.com/paper/2003.12754/) (2020)
- [Document-Level Relation Extraction with Reconstruction](https://mlsanity.com/paper/2012.11384/) (2020)
- [Improving Pairwise Ranking for Multi-label Image Classification](https://mlsanity.com/paper/1704.03135/) (2017)
- [Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification](https://mlsanity.com/paper/1909.04176/) (2019)
- [GDPNet: Refining Latent Multi-View Graph for Relation Extraction](https://mlsanity.com/paper/2012.06780/) (2020)
- [Coarse-to-Fine Entity Representations for Document-level Relation Extraction](https://mlsanity.com/paper/2012.02507/) (2020)

## Built on by (most cited first, 8 of 8)

- [Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction](https://mlsanity.com/paper/2401.13598/) (2024)
- [A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling](https://mlsanity.com/paper/2210.08709/) (2022)
- [Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction](https://mlsanity.com/paper/2305.11029/) (2023)
- [Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction](https://mlsanity.com/paper/2304.00824/) (2023)
- [Asymmetric Polynomial Loss For Multi-Label Classification](https://mlsanity.com/paper/2304.05361/) (2023)
- [A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling](https://mlsanity.com/paper/2306.14806/) (2023)
- [DORE: Document Ordered Relation Extraction based on Generative Framework](https://mlsanity.com/paper/2210.16064/) (2022)
- [On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations](https://mlsanity.com/paper/2406.07444/) (2024)

## Abstract (arXiv)

Document-level relation extraction (RE) aims at extracting relations among entities expressed across multiple sentences, which can be viewed as a multi-label classification problem. In a typical document, most entity pairs do not express any pre-defined relation and are labeled as "none" or "no relation". For good document-level RE performance, it is crucial to distinguish such none class instances (entity pairs) from those of pre-defined classes (relations). However, most existing methods only estimate the probability of pre-defined relations independently without considering the probability of "no relation". This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions. To address this problem, we propose a new multi-label loss that encourages large margins of label confidence scores between each pre-defined class and the none class, which enables captured label correlations and context-dependent thresholding for label prediction. To gain further robustness against positive-negative imbalance and mislabeled data that could appear in real-world RE datasets, we propose a margin regularization and a margin shifting technique. Experimental results demonstrate that our method significantly outperforms existing multi-label losses for document-level RE and works well in other multi-label tasks such as emotion classification when none class instances are available for training.