In-depth analysis of the impact of OCR errors on named entity recognition and linking

Abstract

Named entities (NEs) are among the most relevant type of information that can be used to properly index digital documents and thus easily retrieve them. It has long been observed that NEs are key to accessing the contents of digital library portals as they are contained in most user queries. However, most digitized documents are indexed through their optical character recognition (OCRed) version which include numerous errors. Although OCR engines have considerably improved over the last few years, OCR errors still considerably impact document access. Previous works were conducted to evaluate the impact of OCR errors on named entity recognition (NER) and named entity linking (NEL) techniques separately. In this article, we experimented with a variety of OCRed documents with different levels and types of OCR noise to assess in depth the impact of OCR on named entity processing. We provide a deep analysis of OCR errors that impact the performance of NER and NEL. We then present the resulting exhaustive study and subsequent recommendations on the adequate documents, the OCR quality levels, and the post-OCR correction strategies required to perform reliable NER and NEL.

Intelligent electronic document layout recognition via deep learning

“…Text detection is a crucial component of Optical Character Recognition (OCR) technology [1,2,3]. Traditional text detection methods employ techniques such as binarization and affine transformations to locate text strings.…”

Generalizability in Document Layout Analysis for Scientific Article Figure & Caption Extraction

“…Given this dearth of historical synthetic datasets, there have been several efforts to artificially "age" these newer documents by including effects such as artificial warping, rotation, and simulated dust and random noise on the page. While much focus has been placed on the aging of articles on downstream tasks such as the mining of historical event-related OCR text [24] or named-entity recognition [25], some recent work has focused on the effects of the aging process on the localization of page-objects [10,11] and the generation of new training sets for historical documents [26].…”

A Quantitative Analysis of Noise Impact on Document Ranking

“…Van Strien et al [16], for instance, showed that processing low-quality documents impairs the performance of six NLP tasks including sentence segmentation and dependency parsing. Hamdi et al [17] showed that the performance of named entity recognition systems can have a significant drop of F1-score from 90% to 50% for character error rates between 2% and 30%.…”