arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.00583cs.CL
收藏

历史语料的神经OCR事后修正

Neural OCR Post-Hoc Correction of Historical Corpora

L3S Research Center(L3S研究中心);Leibniz University of Hannover(莱布尼茨汉诺威大学);Austrian National Library(奥地利国家图书馆);Amazon(亚马逊)

Lijun Lyu, Maria Koutraki, Martin Krickl, Besnik Fetahu

摘要:

光学字符识别(OCR)对于更深入地访问历史收藏至关重要。OCR需要考虑拼写变化、字体或语言演变(即,新字母、单词拼写)作为字符、单词或分词转录错误的主要来源。对于历史印刷品的数字语料库,由于扫描质量低和缺乏语言标准化,错误进一步加剧。对于OCR事后纠正任务,我们提出了一种基于递归(RNN)和深度卷积网络(ConvNet)组合的神经方法来纠正OCR转录错误。在字符级,我们灵活地捕捉错误,并解码的基础上,一种新的注意力机制的正确输出。考虑到输入和输出的相似性,我们提出了一个新的损失函数,奖励模型的纠正行为。在德语历史书籍语料库上的评估表明,我们的模型是强大的,在捕捉各种OCR转录错误和减少单词出错率的32.3%,超过89%。

英文摘要:

Optical character recognition (OCR) is crucial for a deeper access to historical collections. OCR needs to account for orthographic variations, typefaces, or language evolution (i.e., new letters, word spellings), as the main source of character, word, or word segmentation transcription errors. For digital corpora of historical prints, the errors are further exacerbated due to low scan quality and lack of language standardization. For the task of OCR post-hoc correction, we propose a neural approach based on a combination of recurrent (RNN) and deep convolutional network (ConvNet) to correct OCR transcription errors. At character level we flexibly capture errors, and decode the corrected output based on a novel attention mechanism. Accounting for the input and output similarity, we propose a new loss function that rewards the model's correcting behavior. Evaluation on a historical book corpus in German language shows that our models are robust in capturing diverse OCR transcription errors and reduce the word error rate of 32.3% by more than 89%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑