Bjørn-Richard Pedersen
Biographic Data
| ID | 9450993 |
|---|---|
| NAME | Bjørn-Richard Pedersen |
| GIVEN NAMES | Bjørn-Richard |
| FAMILY NAME | Pedersen |
| SIGNATURE | PEDERSEN B |
| AFFILIATIONS | UiT The Arctic University of Norway |
| ORCID | 0009-0000-2363-0791 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 2 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2022 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 0 |
More Efficient Manual Review of Automatically Transcribed Tabular Data
Any machine learning method for transcribing historical text requires manual verification and correction, which is often time-consuming and expensive. Our aim is to make it more efficient. Previously, we developed a machine learning model to transcribe 2.3 million handwritten occupation codes from the Norwegian 1950 census. Here, we manually review the 90,000 codes (3%) for which our model had the lowest confidence scores. We allocated these code…
Lessons Learned Developing and Using a Machine Learning Model to Automatically Transcribe 2.3 Million Handwritten Occupation Codes
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 …
No prominent works on this page.
Lessons Learned Developing and Using a Machine Learning Model to Automatically Transcribe 2.3 Million Handwritten Occupation Codes
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 …
More Efficient Manual Review of Automatically Transcribed Tabular Data
Any machine learning method for transcribing historical text requires manual verification and correction, which is often time-consuming and expensive. Our aim is to make it more efficient. Previously, we developed a machine learning model to transcribe 2.3 million handwritten occupation codes from the Norwegian 1950 census. Here, we manually review the 90,000 codes (3%) for which our model had the lowest confidence scores. We allocated these code…
Computer Science (2 works) · Natural language processing (2 works) · Natural Language Processing Techniques (2 works) · Artificial Intelligence (1 works) · Correctness (1 works) · Data Mining Algorithms and Applications (1 works) · Handwritten Text Recognition Techniques (1 works) · Image Processing and 3D Reconstruction (1 works) · Information retrieval (1 works) · Machine learning (1 works)