# A Walk-based Model on Entity Graphs for Relation Extraction

arXiv: https://arxiv.org/abs/1902.07023 · HTML: https://mlsanity.com/paper/1902.07023/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2019.

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

- [A Survey on Extraction of Causal Relations from Natural Language Text](https://mlsanity.com/paper/2101.06426/) (2021)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [Multi-view Inference for Relation Extraction with Uncertain Knowledge](https://mlsanity.com/paper/2104.13579/) (2021)
- [A Comprehensive Survey of Document-level Relation Extraction (2016-2023)](https://mlsanity.com/paper/2309.16396/) (2023)
- [Enriched Attention for Robust Relation Extraction](https://mlsanity.com/paper/2104.10899/) (2021)
- [CEntRE: A paragraph-level Chinese dataset for Relation Extraction among Enterprises](https://mlsanity.com/paper/2210.10581/) (2022)
- [Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence](https://mlsanity.com/paper/2103.03509/) (2021)
- [Distantly Supervised Morpho-Syntactic Model for Relation Extraction](https://mlsanity.com/paper/2401.10002/) (2024)

## Abstract (arXiv)

We present a novel graph-based neural network model for relation extraction. Our model treats multiple pairs in a sentence simultaneously and considers interactions among them. All the entities in a sentence are placed as nodes in a fully-connected graph structure. The edges are represented with position-aware contexts around the entity pairs. In order to consider different relation paths between two entities, we construct up to l-length walks between each pair. The resulting walks are merged and iteratively used to update the edge representations into longer walks representations. We show that the model achieves performance comparable to the state-of-the-art systems on the ACE 2005 dataset without using any external tools.