# Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction

arXiv: https://arxiv.org/abs/2212.14270 · HTML: https://mlsanity.com/paper/2212.14270/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 29 Dec 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Classifying Relations by Ranking with Convolutional Neural Networks](https://mlsanity.com/paper/1504.06580/) (2015)
- [Relation Classification with Entity Type Restriction](https://mlsanity.com/paper/2105.08393/) (2021)
- [GDPNet: Refining Latent Multi-View Graph for Relation Extraction](https://mlsanity.com/paper/2012.06780/) (2020)
- [Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data](https://mlsanity.com/paper/1906.08931/) (2019)
- [Multi-view Inference for Relation Extraction with Uncertain Knowledge](https://mlsanity.com/paper/2104.13579/) (2021)
- [Long-tailed Distribution Adaptation](https://mlsanity.com/paper/2110.02686/) (2021)
- [SEE: Syntax-aware Entity Embedding for Neural Relation Extraction](https://mlsanity.com/paper/1801.03603/) (2018)
- [Improving Tail-Class Representation with Centroid Contrastive Learning](https://mlsanity.com/paper/2110.10048/) (2021)
- [Global Relation Embedding for Relation Extraction](https://mlsanity.com/paper/1704.05958/) (2017)

## Built on by (most cited first, 10 of 10)

- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [An Empirical Study on Information Extraction using Large Language Models](https://mlsanity.com/paper/2305.14450/) (2023)
- [Retrieval-Augmented Generation-based Relation Extraction](https://mlsanity.com/paper/2404.13397/) (2024)
- [Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction](https://mlsanity.com/paper/2404.17809/) (2024)
- [Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks](https://mlsanity.com/paper/2406.14745/) (2024)
- [MPL: Multiple Programming Languages with Large Language Models for Information Extraction](https://mlsanity.com/paper/2505.16107/) (2025)
- [Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning Environment](https://mlsanity.com/paper/2310.10590/) (2023)
- [Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks](https://mlsanity.com/paper/2312.08726/) (2023)
- [A Two Dimensional Feature Engineering Method for Relation Extraction](https://mlsanity.com/paper/2404.04959/) (2024)
- [A Structured Literature Review on Traditional Approaches in Current Natural Language Processing](https://mlsanity.com/paper/2505.12970/) (2025)

## Abstract (arXiv)

The typical way for relation extraction is fine-tuning large pre-trained language models on task-specific datasets, then selecting the label with the highest probability of the output distribution as the final prediction. However, the usage of the Top-k prediction set for a given sample is commonly overlooked. In this paper, we first reveal that the Top-k prediction set of a given sample contains useful information for predicting the correct label. To effectively utilizes the Top-k prediction set, we propose Label Graph Network with Top-k Prediction Set, termed as KLG. Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them. We also design a dynamic k-selection mechanism to learn more powerful and discriminative relation representation. Our experiments show that KLG achieves the best performances on three relation extraction datasets. Moreover, we observe that KLG is more effective in dealing with long-tailed classes.