Untitled

Mittendorf, Elke; Schäuble, Peter

doi:10.1023/a:1026564708926

Cited by 18 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mittendorf et al investigated how robust IR systems are toward OCR errors in digitized documents [9]. They found that longer documents describing a single topic redundantly have a better chance of retrieval than documents that are either short or discuss different topics.…”

Section: Related Work 21 Ocr Quality and Retrievalmentioning

confidence: 99%

Impact of Crowdsourcing OCR Improvements on Retrievability Bias

Traub

Samar

Ossenbruggen

et al. 2018

Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries

View full text Add to dashboard Cite

Digitized document collections often suffer from OCR errors that may impact a document's readability and retrievability. We studied the effects of correcting OCR errors on the retrievability of documents in a historic newspaper corpus of a digital library. We computed retrievability scores for the uncorrected documents using queries from the library's search log, and found that the document OCR character error rate and retrievability score are strongly correlated. We computed retrievability scores for manually corrected versions of the same documents, and report on differences in their total sum, the overall retrievability bias, and the distribution of these changes over the documents, queries and query terms. For large collections, often only a fraction of the corpus is manually corrected. Using a mixed corpus, we assess how this mix affects the retrievability of the corrected and uncorrected documents. The correction of OCR errors increased the number of documents retrieved in all conditions. The increase contributed to a less biased retrieval, even when taking the potential lower ranking of uncorrected documents into account. CCS CONCEPTS• Information systems → Query log analysis; Evaluation of retrieval results;

show abstract

Section: Related Work 21 Ocr Quality and Retrievalmentioning

confidence: 99%

Impact of Crowdsourcing OCR Improvements on Retrievability Bias

Traub

Samar

Ossenbruggen

et al. 2018

Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries

View full text Add to dashboard Cite

show abstract

“…Tanner et al (2009) suggest that word accuracy rates less than 80% are harmful for search, but when the word accuracy is over 80%, fuzzy search capabilities of search engines should manage the problems caused by word errors. Mittendorf and Schäuble's (2000) probabilistic model for data corruption seems to support this. Information retrieval is robust even with corrupted data, but IR works best with longer documents and long queries.…”

Section: Discussionmentioning

confidence: 84%

“…Besides retrieval performance effects poor OCR quality has an effect on ranking of the documents (Taghva et al 1996;Mittendorf and Schäuble 2000). In practice these kinds of drops in retrieval and ranking performance mean that the user will lose relevant documents: either they are not found at all by the search engine or the documents are so low in the ranking list that the user may skip them.…”

Section: Discussionmentioning

confidence: 99%

How to Do Lexical Quality Estimation of a Large OCRed Historical Finnish Newspaper Collection with Scarce Resources

Kettunen

2020

Digital Studies/Le Champ Numérique

View full text Add to dashboard Cite

show abstract

“…We could of course try to correct these errors in post-processimg with a dictionary, however existing work [14] indicates that this can introduce more problems for information retrieval due to false substitutions than it solves. We thus do not explore dictionarybased substitution methods.…”

Section: Baseline and Standard Prf Resultsmentioning

confidence: 99%

Using String Comparison in Context for Improved Relevance Feedback in Different Text Media

Lam-Adesina

Jones

2006

String Processing and Information Retrieval

View full text Add to dashboard Cite

Abstract. Query expansion is a long standing relevance feedback technique for improving the effectiveness of information retrieval systems. Previous investigations have shown it to be generally effective for electronic text, to give proportionally better improvement for automatic transcriptions of spoken documents, and to be at best of questionable utility for optical character recognized scanned text documents. We introduce two corpus-based methods based on using a stringedit distance measure in context to automatically detect and correct transcription errors. One method operates at query-time and requires no modification of the document index file, and the other at index-time and operates using the standard query-time expansion process. Experimental investigations show these methods to produce improvements in relevance feedback for all three media types, but most significantly mean that relevance feedback can now successfully be applied to scanned text documents.

show abstract

Untitled

Cited by 18 publications

References 18 publications

Impact of Crowdsourcing OCR Improvements on Retrievability Bias

Impact of Crowdsourcing OCR Improvements on Retrievability Bias

How to Do Lexical Quality Estimation of a Large OCRed Historical Finnish Newspaper Collection with Scarce Resources

Using String Comparison in Context for Improved Relevance Feedback in Different Text Media

Contact Info

Product

Resources

About