Manually validated PageXML files for images in "Diario del soldato Bruno Celestino"

Transcribed diary of Italian soldier Bruno Celestino in World War I (52 pages in total) in PageXML format (pages 2 to 49 were transcribed). These files are useful for training a handwritten text recognition model. The PageXML files were created by applying Transkribus' Italian Handwriting M1 model (https://readcoop.eu/model/italian-general-model/) on the images at https://europeana.transcribathon.eu/documents/story/?story=110659, automatically correcting the output using the flat-text manual transcription available with these images, and manually validating the resulting PageXML files. The software for automatically correcting OCR output using flat-text manual transcriptions (and hence adding a link between image and text not present in the flat-text files) has been developed as part of the AI4Culture project (https://pro.europeana.eu/project/ai4culture-an-ai-platform-for-the-cultural-heritage-data-space).本数据集为第一次世界大战意大利士兵布鲁诺·切莱斯蒂诺（Bruno Celestino）的转录日记，共计52页，采用PageXML（PageXML）格式，仅完成第2至49页的转录工作。该数据集可用于训练手写文本识别模型。 本数据集的PageXML文件生成流程如下：将Transkribus意大利手写体M1模型（https://readcoop.eu/model/italian-general-model/）应用于https://europeana.transcribathon.eu/documents/story/?story=110659 处的图像资源，再利用该图像配套的纯文本手动转录结果自动校正模型输出，并对最终生成的PageXML文件进行人工校验。 用于基于纯文本手动转录结果自动校正光学字符识别（Optical Character Recognition, OCR）输出（同时补充纯文本文件中缺失的图像与文本间关联）的软件，系AI4Culture项目（https://pro.europeana.eu/project/ai4culture-an-ai-platform-for-the-cultural-heritage-data-space）的开发成果之一。