Training of machine-learning based procedures for automated postcorrection of OCRed historical printings

基于机器学习的程序培训，用于 ORed 历史打印的自动后期校正

• 批准号: 431091758
• 负责人: Professor Dr. Klaus U. Schulz
• 金额: --
• 依托单位: Centrum für Informations- und Sprachverarbeitung (CIS)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2020
• 资助国家: 德国
• 起止时间: 2019-12-31 至 2021-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/431091758?language=en
• 关键词: Training; machine; learning; based; procedures

OCR-results for historical printings typically contain many recognition errors. Hence postcorrection methods play an important role in this field. Some automated postcorrection systems ``individually'' developed for a particular historical OCR-corpus have shown good results. However, the development of an ``omnipotent'' general system for automated postcorrection of OCR-results, offering good results for distinct OCR engines and arbitrary historical printings, is an ambitious future goal. In the framework of the OCR-D initiative currently OCR postcorrection systems are being developed that are based on supervised machine learning. In the ideal case these systems should be applicable to arbitrary OCR engines and historical texts. In this project we want to systematically study the influence of training data and -methods on the quality of the correction results achieved. The long-term ultimate goal is the development of an ``omnipotent'' (s.a.) postcorrection model. As a first step we look for training data and feature systems that lead to optimal correction results for specific OCR engines and classes of historical printings, analyzing correction problems arising for other OCRs and corpora. Using these results as a starting point we search for methods to minimize the additional effort needed (in terms of ground truth preparation and posttraining) for developing correction models for larger and inhomogeneous corpora. Specific points to be investigated are, among others, the combination of postcorrection models and the automated selection of a correction model for a given new OCR corpus.

OCR-历史打印的结果通常包含许多识别错误。因此，后校正法在这一领域发挥着重要的作用。针对特定的历史OCR语料库开发的一些“单独”的自动后校正系统显示了良好的效果。然而，开发一种用于OCR结果自动后校正的“万能”通用系统，为不同的OCR引擎和任意的历史打印提供良好的结果，是一个雄心勃勃的未来目标。在光学字符识别-D倡议的框架内，目前正在开发基于有监督机器学习的光学字符识别后校正系统。在理想情况下，这些系统应该适用于任意的OCR引擎和历史文本。在这个项目中，我们想要系统地研究训练数据和方法对校正结果质量的影响。长期的最终目标是发展一种“万能的”(S.A.)后校正模型。作为第一步，我们寻找训练数据和特征系统，以导致特定OCR引擎和历史打印类别的最佳校正结果，并分析其他OCR和语料库出现的校正问题。以这些结果为起点，我们寻找方法，以最大限度地减少为更大和不同质的语料库开发更正模型所需的额外工作(在实地真相准备和后期培训方面)。除其他外，要研究的具体问题包括校正后模型的组合以及针对给定的新OCR语料库自动选择校正模型。