Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit
This work addresses the lack of resources for Romanised Sanskrit OCR, enabling more accurate digitization of texts in this domain, though it is incremental as it builds on existing OCR and sequence-to-sequence methods.
The paper tackles the problem of digitizing Romanised Sanskrit texts by proposing a post-OCR correction approach that reuses OCR models trained for other Roman-script languages, achieving a Character Recognition Rate (CRR) of 87.01% from an initial OCR output with 35.76% CRR and a 7.69% increase over the state-of-the-art model.
We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit. Owing to the lack of resources our approach uses OCR models trained for other languages written in Roman. Currently, there exists no dataset available for Romanised Sanskrit OCR. So, we bootstrap a dataset of 430 images, scanned in two different settings and their corresponding ground truth. For training, we synthetically generate training images for both the settings. We find that the use of copying mechanism (Gu et al., 2016) yields a percentage increase of 7.69 in Character Recognition Rate (CRR) than the current state of the art model in solving monotone sequence-to-sequence tasks (Schnober et al., 2016). We find that our system is robust in combating OCR-prone errors, as it obtains a CRR of 87.01% from an OCR output with CRR of 35.76% for one of the dataset settings. A human judgment survey performed on the models shows that our proposed model results in predictions which are faster to comprehend and faster to improve for a human than the other systems.