# Leveraging Subword Embeddings for Multinational Address Parsing

arXiv: https://arxiv.org/abs/2006.16152 · HTML: https://mlsanity.com/paper/2006.16152/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

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

- [Multinational Address Parsing: A Zero-Shot Evaluation](https://mlsanity.com/paper/2112.04008/) (2021)
- [Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data](https://mlsanity.com/paper/2404.05632/) (2024)
- [Deepparse : An Extendable, and Fine-Tunable State-Of-The-Art Library for Parsing Multinational Street Addresses](https://mlsanity.com/paper/2311.11846/) (2023)
- [Toward building next-generation Geocoding systems: a systematic review](https://mlsanity.com/paper/2503.18888/) (2025)
- [What's in the laundromat? Mapping and characterising offshore owned domestic property in London](https://mlsanity.com/paper/2207.10931/) (2022)
- [Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach](https://mlsanity.com/paper/2311.13222/) (2023)

## Abstract (arXiv)

Address parsing consists of identifying the segments that make up an address such as a street name or a postal code. Because of its importance for tasks like record linkage, address parsing has been approached with many techniques. Neural network methods defined a new state-of-the-art for address parsing. While this approach yielded notable results, previous work has only focused on applying neural networks to achieve address parsing of addresses from one source country. We propose an approach in which we employ subword embeddings and a Recurrent Neural Network architecture to build a single model capable of learning to parse addresses from multiple countries at the same time while taking into account the difference in languages and address formatting systems. We achieved accuracies around 99 % on the countries used for training with no pre-processing nor post-processing needed. We explore the possibility of transferring the address parsing knowledge obtained by training on some countries' addresses to others with no further training in a zero-shot transfer learning setting. We achieve good results for 80 % of the countries (33 out of 41), almost 50 % of which (20 out of 41) is near state-of-the-art performance. In addition, we propose an open-source Python implementation of our trained models.