arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.02622cs.CL
收藏

OCR后纠错的词汇感知半监督学习

Lexically Aware Semi-Supervised Learning for OCR Post-Correction

Carnegie Mellon University(卡内基梅隆大学);University of British Columbia(不列颠哥伦比亚大学);George Mason University(乔治梅森大学)

Shruti Rijhwani, Daisy Rosenblum, Antonios Anastasopoulos, Graham Neubig

摘要:

世界上许多语言的大部分现有语言数据都被锁在非数字化的书籍和文件中。光学字符识别(OCR)可用于产生数字化文本,并且先前的工作已经证明了神经后校正方法的实用性,该方法改善了通用OCR系统在识别资源较少的语言上的结果。然而,这些方法依赖于手动管理的校正后数据,与需要数字化的未注释原始图像相比,这些数据相对较少。在本文中,我们提出了一种半监督学习方法,该方法可以利用这些原始图像来提高性能,特别是通过使用自训练,一种模型在其自身输出上迭代训练的技术。此外,为了加强识别词汇的一致性,我们引入了一种词汇感知解码方法,该方法使用基于计数的语言模型从识别文本构建神经后校正模型,使用加权有限状态自动机(WFSA)进行高效和有效的解码。四种濒危语言的结果证明了所提出的方法的实用性,相对误差减少了15- 29%,我们发现自我训练和词汇感知解码的结合对于实现一致的改进至关重要。数据和代码可在https://shrutirij.github.io/ocr-el/上获得。

英文摘要:

Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Optical character recognition (OCR) can be used to produce digitized text, and previous work has demonstrated the utility of neural post-correction methods that improve the results of general-purpose OCR systems on recognition of less-well-resourced languages. However, these methods rely on manually curated post-correction data, which are relatively scarce compared to the non-annotated raw images that need to be digitized. In this paper, we present a semi-supervised learning method that makes it possible to utilize these raw images to improve performance, specifically through the use of self-training, a technique where a model is iteratively trained on its own outputs. In addition, to enforce consistency in the recognized vocabulary, we introduce a lexically-aware decoding method that augments the neural post-correction model with a count-based language model constructed from the recognized texts, implemented using weighted finite-state automata (WFSA) for efficient and effective decoding. Results on four endangered languages demonstrate the utility of the proposed method, with relative error reductions of 15-29%, where we find the combination of self-training and lexically-aware decoding essential for achieving consistent improvements. Data and code are available at https://shrutirij.github.io/ocr-el/.

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。

↑