- 期刊
- OpenAccess
Language Model Assisted OCR Classification for Republican Chinese Newspaper Text
以語言模型輔助民國報紙文本的光學字元辨識分類
摘要
In this work, we present methods to obtain a neural optical character recognition (OCR) tool for article blocks in a Republican Chinese newspaper. Our basis is a small fraction of the image corpus for which text ground truth exists. We introduce a character segmentation method which produces over 90,000 labeled images of single characters and train a GoogLeNet classifier as an OCR model. In addition, we create synthetic training data from character images extracted from Song-Ti fonts. Randomly augmented on the fly and used for pre-training, they increase OCR accuracy from 95.49% to 96.95% on our test set. Finally, we employ post-OCR correction based on a pre-trained masked language model and present heuristics to select the required hyperparameters, by which we are able to correct 16% of remaining classification errors, increasing accuracy on the test set to 97.44%.
並列摘要
本文為研發使用神經網絡的光學字元辨識（optical character recognition, OCR）工具提出了一些方法，以辨識民國時期中文報紙中的文章部分。這項工作的基礎為一小部分已存在基準真相（ground truth）的圖像語料。我們引入了一種字符分割方法，從而生成了超過90,000個有標籤的單一字符圖像，並且訓練了一個GoogLeNet分類器作為OCR模型。此外，我們從宋體字體中提取字符圖像，以此製作了訓練數據。這些圖像被隨機增強並被用於預訓練，測試集的OCR準確率由95.49%提高到96.95%。最後，我們採用了基於預訓練遮罩語言模型（Masked LM）的OCR後校正，並提出啟發式方法來選擇所需的超參數。通過這些方法，我們能夠校正16%的剩餘分類錯誤，將測試集的準確率提高到97.44%。