# Mordecai 3: A Neural Geoparser and Event Geocoder

arXiv: https://arxiv.org/abs/2303.13675 · HTML: https://mlsanity.com/paper/2303.13675/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 4 of 4)

- [A Pragmatic Guide to Geoparsing Evaluation](https://mlsanity.com/paper/1810.12368/) (2018)
- [A Coherent Unsupervised Model for Toponym Resolution](https://mlsanity.com/paper/1805.01952/) (2018)
- [Regressing Location on Text for Probabilistic Geocoding](https://mlsanity.com/paper/2107.00080/) (2021)
- [Geolocating Political Events in Text](https://mlsanity.com/paper/1905.12713/) (2019)

## Built on by (most cited first, 6 of 6)

- [GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding](https://mlsanity.com/paper/2310.14478/) (2023)
- [AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters](https://mlsanity.com/paper/2401.06408/) (2024)
- [GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding](https://mlsanity.com/paper/2408.11366/) (2024)
- [Assessing socio-economic climate impacts from text data](https://mlsanity.com/paper/2605.20793/) (2026)
- [RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles](https://mlsanity.com/paper/2501.11440/) (2025)
- [Identifying the Geographic Foci of US Local News](https://mlsanity.com/paper/2603.00787/) (2026)

## Abstract (arXiv)

Mordecai3 is a new end-to-end text geoparser and event geolocation system. The system performs toponym resolution using a new neural ranking model to resolve a place name extracted from a document to its entry in the Geonames gazetteer. It also performs event geocoding, the process of linking events reported in text with the place names where they are reported to occur, using an off-the-shelf question-answering model. The toponym resolution model is trained on a diverse set of existing training data, along with several thousand newly annotated examples. The paper describes the model, its training process, and performance comparisons with existing geoparsers. The system is available as an open source Python library, Mordecai 3, and replaces an earlier geoparser, Mordecai v2, one of the most widely used text geoparsers (Halterman 2017).