English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Word error rate of an ocr is often higher than its character error rate. Thisis especially true when ocrs are designed by recognizing characters. High wordaccuracies are critical to tasks like the creation of content in digitallibraries and text-to-speech applications. In order to detect and correct themisrecognised words, it is common for an ocr module to employ a post-processorto further improve the word accuracy. However, conventional approaches topost-processing like looking up a dictionary or using a statistical languagemodel (slm), are still limited. In many such scenarios, it is often required toremove the outstanding errors manually. We observe that the traditionalpost-processing schemes look at error words sequentially since ocrs processdocuments one at a time. We propose a cost-efficient model to address the errorwords in batches rather than correcting them individually. We exploit the factthat a collection of documents, unlike a single document, has a structureleading to repetition of words. Such words, if efficiently grouped together andcorrected as a whole can lead to a significant reduction in the cost.Correction can be fully automatic or with a human in the loop. Towards this, weemploy a novel clustering scheme to obtain fairly homogeneous clusters. Wecompare the performance of our model with various baseline approaches includingthe case where all the errors are removed by a human. We demonstrate theefficacy of our solution empirically by reporting more than 70% reduction inthe human effort with near perfect error correction. We validate our method onBooks from multiple languages.

A Cost Efficient Approach to Correct OCR Errors in Large Document Collections