# Discourse-level Relation Extraction via Graph Pooling

arXiv: https://arxiv.org/abs/2101.00124 · HTML: https://mlsanity.com/paper/2101.00124/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 1 Jan 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [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)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [Reasoning with Latent Structure Refinement for Document-Level Relation Extraction](https://mlsanity.com/paper/2005.06312/) (2020)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Attention Guided Graph Convolutional Networks for Relation Extraction](https://mlsanity.com/paper/1906.07510/) (2019)
- [Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs](https://mlsanity.com/paper/1909.00228/) (2019)
- [Distant Supervision for Relation Extraction beyond the Sentence Boundary](https://mlsanity.com/paper/1609.04873/) (2016)
- [HARP: Hierarchical Representation Learning for Networks](https://mlsanity.com/paper/1706.07845/) (2017)
- [Document-Level N-ary Relation Extraction with Multiscale Representation Learning](https://mlsanity.com/paper/1904.02347/) (2019)
- [Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network](https://mlsanity.com/paper/1906.04684/) (2019)
- [Document-Level Relation Extraction with Reconstruction](https://mlsanity.com/paper/2012.11384/) (2020)
- [MILE: A Multi-Level Framework for Scalable Graph Embedding](https://mlsanity.com/paper/1802.09612/) (2018)

## Built on by (most cited first, 9 of 9)

- [Hierarchical Fine-Grained Image Forgery Detection and Localization](https://mlsanity.com/paper/2303.17111/) (2023)
- [Multi-domain Learning for Updating Face Anti-spoofing Models](https://mlsanity.com/paper/2208.11148/) (2022)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [TAGPRIME: A Unified Framework for Relational Structure Extraction](https://mlsanity.com/paper/2205.12585/) (2022)
- [Multi-hop Evidence Retrieval for Cross-document Relation Extraction](https://mlsanity.com/paper/2212.10786/) (2022)
- [Contextual Label Projection for Cross-Lingual Structured Prediction](https://mlsanity.com/paper/2309.08943/) (2023)
- [Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network](https://mlsanity.com/paper/2312.02224/) (2023)
- [SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness](https://mlsanity.com/paper/2410.18393/) (2024)
- [Controllable Text Generation for Open-Domain Creativity and Fairness](https://mlsanity.com/paper/2209.12099/) (2022)

## Abstract (arXiv)

The ability to capture complex linguistic structures and long-term dependencies among words in the passage is essential for discourse-level relation extraction (DRE) tasks. Graph neural networks (GNNs), one of the methods to encode dependency graphs, have been shown effective in prior works for DRE. However, relatively little attention has been paid to receptive fields of GNNs, which can be crucial for cases with extremely long text that requires discourse understanding. In this work, we leverage the idea of graph pooling and propose to use pooling-unpooling framework on DRE tasks. The pooling branch reduces the graph size and enables the GNNs to obtain larger receptive fields within fewer layers; the unpooling branch restores the pooled graph to its original resolution so that representations for entity mention can be extracted. We propose Clause Matching (CM), a novel linguistically inspired graph pooling method for NLP tasks. Experiments on two DRE datasets demonstrate that our models significantly improve over baselines when modeling long-term dependencies is required, which shows the effectiveness of the pooling-unpooling framework and our CM pooling method.