# Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features

arXiv: https://arxiv.org/abs/2607.19718 · HTML: https://mlsanity.com/paper/2607.19718/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Graph Convolution over Pruned Dependency Trees Improves Relation Extraction](https://mlsanity.com/paper/1809.10185/) (2018)
- [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)
- [Attention Guided Graph Convolutional Networks for Relation Extraction](https://mlsanity.com/paper/1906.07510/) (2019)
- [We Need to Talk About Random Splits](https://mlsanity.com/paper/2005.00636/) (2020)
- [Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation](https://mlsanity.com/paper/2102.01818/) (2021)
- [Named Entity Recognition and Classification on Historical Documents: A Survey](https://mlsanity.com/paper/2109.11406/) (2021)
- [A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice](https://mlsanity.com/paper/2404.16958/) (2024)
- [Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction](https://mlsanity.com/paper/2004.08134/) (2020)
- [Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts](https://mlsanity.com/paper/2606.25935/) (2026)
- [LightRel SemEval-2018 Task 7: Lightweight and Fast Relation Classification](https://mlsanity.com/paper/1804.08426/) (2018)

## Abstract (arXiv)

The HIPE-2026 shared task introduces person-place relation extraction from multilingual historical newspapers as a new evaluation track, classifying the at and isAt relations between pre-annotated person and location mentions in English, French, and German. Motivated by the cost of processing historical archives at scale, our team (DS@GT HIPE, team 2 in the official results) investigates how far a lightweight, interpretable system can go without any pretrained language model at the relation classification stage. Our approach builds a document-level graph from dependency parses, extracts proximity-based and part-of-speech features for each entity pair, and classifies them with small scikit-learn ensembles or compact Graph Attention Networks, keeping every submitted run under 847K parameters. On the official evaluation (Test A, the newspaper test set), our best run reached a macro recall of 0.5142, ranking 3rd on the Efficiency profile while placing mid-table on Accuracy among the 17 participating teams. Two findings stand out. First, minimum character distance alone captures most of the classification signal; adding further engineered features yields inconsistent gains and sometimes degrades performance, echoing prior evidence that argument distance dominates relation extraction. Second, document-grouped cross-validation is essential on this corpus: pair-level splits inflate scores by 25-37 percentage points because entity mentions recur across documents, a data-leakage effect that grouped cross-validation removes.