# Lessons learned developing and using a machine learning model to automatically transcribe 2.3 million handwritten occupation codes

arXiv: https://arxiv.org/abs/2106.03996 · HTML: https://mlsanity.com/paper/2106.03996/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 28 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 3 of 3)

- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Convolutional Neural Networks for Page Segmentation of Historical Document Images](https://mlsanity.com/paper/1704.01474/) (2017)
- [Applications of Machine Learning in Document Digitisation](https://mlsanity.com/paper/2102.03239/) (2021)

## Built on by (most cited first, 1 of 1)

- [More efficient manual review of automatically transcribed tabular data](https://mlsanity.com/paper/2306.16126/) (2023)

## Abstract (arXiv)

Machine learning approaches achieve high accuracy for text recognition and are therefore increasingly used for the transcription of handwritten historical sources. However, using machine learning in production requires a streamlined end-to-end pipeline that scales to the dataset size and a model that achieves high accuracy with few manual transcriptions. The correctness of the model results must also be verified. This paper describes our lessons learned developing, tuning and using the Occode end-to-end machine learning pipeline for transcribing 2.3 million handwritten occupation codes from the Norwegian 1950 population census. We achieve an accuracy of 97% for the automatically transcribed codes, and we send 3% of the codes for manual verification. We verify that the occupation code distribution found in our results matches the distribution found in our training data, which should be representative for the census as a whole. We believe our approach and lessons learned may be useful for other transcription projects that plan to use machine learning in production. The source code is available at: https://github.com/uit-hdl/rhd-codes