Mordecai 3: A Neural Geoparser and Event Geocoder
Not on the map. Why?
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).
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 4 of its 15 references that are in the map. First posted on arXiv 23 Mar 2023.
Builds on
4 of 15 references.
References · 4
- 2018A Pragmatic Guide to Geoparsing Evaluationcited by 17
- 2018A Coherent Unsupervised Model for Toponym Resolutioncited by 8
- 2021Regressing Location on Text for Probabilistic Geocodingcited by 5
- 2019Geolocating Political Events in Textcited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 2.
6 papers.
- 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understandingcited by 37
- 2024AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filterscited by 21
- 2024GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understandingcited by 10
- 2026Assessing socio-economic climate impacts from text datacited by 1
- 2025RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articlescited by 0
- 2026Identifying the Geographic Foci of US Local Newscited by 0
- 2026Assessing socio-economic climate impacts from text data20 May 2026
- 2026Identifying the Geographic Foci of US Local News28 Feb 2026
- 2025RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles20 Jan 2025
- 2024GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding21 Aug 2024
- 2024AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters12 Jan 2024
- 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding23 Oct 2023