On lexical resources for digitization of historical documents

Gotscharek, Annette; Reffle, Ulrich; Ringlstetter, Christoph; Schulz, Klaus U.

doi:10.1145/1600193.1600236

Cited by 14 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite high image quality and standard typeface, OCR word accuracy is only 86.65%, which is much worse than for modern languages; Holley [2] classifies this as "poor accuracy". It is due to the fact that the OCR software is unaware of the special characters and the lack of lexicons or other linguistic resources for historical language variants, which also do not have standardized orthographies (see Gotscharek et al [1] on the issue of language resources). While mif2html required software development, our experiments with text samples indicate that training the OCR software or correcting its output would both require an inordinate amount of human labor to produce any significant effect.…”

Section: Discussionmentioning

confidence: 99%

“…1 Even though FrameMaker documents are generally portable between the Macintosh, UNIX, and Windows versions of FrameMaker, the character encoding is always platform-specific. The character encoding of our documents is MacRoman.…”

Section: Character Encodingmentioning

confidence: 99%

“…Ultimately, we want to produce TEI-conforming XML [9], but due to the complexity of the documents, a one-step upconversion is 1 Unicode support was only added in 2007 with FrameMaker 8. not feasible. We therefore decided to first convert MIF into XHTML with an associated CSS stylesheet that captures as much information from the original MIF as possible and which can then be used for further processing.…”

Section: Approachmentioning

confidence: 99%

See 2 more Smart Citations

Document conversion for cultural heritage texts

Piotrowski¹

2010

Proceedings of the 10th ACM Symposium on Document Engineering

View full text Add to dashboard Cite

Many large-scale digitization projects are currently under way that intend to preserve the cultural heritage contained in paper documents (in particular books) and make it available on the Web. Typically OCR is used to produce searchable electronic texts from books. For newer books, approximately from the late 1980s onwards, digital text may already exist in the form of typesetting data. For applications that require a higher level of accuracy than OCR can deliver, the conversion of typesetting data can thus be an alternative to manual keying. In this paper, we describe a tool for converting typesetting data in FrameMaker format to XHTML+CSS developed for a collection of source editions of medieval and early modern documents. Even though the books of the Collection are typeset in good quality and in modern typefaces, OCR is unusable, since the text is in various historical forms of German, French, Italian, Rhaeto-Romanic, and Latin. The conversion of typesetting data produces fully reliable text free from OCR errors and thus also provides a basis for the construction of language resources for the processing of historical texts.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Character Encodingmentioning

confidence: 99%

Section: Approachmentioning

confidence: 99%

See 1 more Smart Citation

Document conversion for cultural heritage texts

Piotrowski¹

2010

Proceedings of the 10th ACM Symposium on Document Engineering

View full text Add to dashboard Cite

show abstract

“…Just as humans rely on dictionaries to understand, access and navigate cultural heritage so, too, do machines. Presently, dictionaries play a crucial role in many kinds of computational systems; for example, multilingual data processing and interchange (see, inter alia, Dietrich 2010); machine translation (see, inter alia, Aljlayl et al 2011); and information retrieval (see, inter alia, Gotscharek et al 2009). While sophisticated search engines deliver an abundance of information, one of the greatest on-going challenges of modern day information technology is to make this abundance manageable.…”

Section: For Man and Machine: The Changing Role Of The Digital Dictiomentioning

confidence: 99%

New Publication Cultures in the Humanities: Exploring the Paradigm Shift

Das¹

2016

J. Scientomet Res.

View full text Add to dashboard Cite

“…There have been a lot of work in preserving books in the form of scanned images, digitizing scanned pages using OCR engines and crowdsourcing, analyzing digital data, and building archive explorers [21,6,17,37,7,64,44,61,60]. While OCR engines offer a scalable mechanism to digitize scanned images, they have limited accuracy or no support for many of the world's popular languages, hence automating digitization work-flow [52] is not feasible.…”

Section: Related Workmentioning

confidence: 99%

Improving Accessibility of Archived Raster Dictionaries of Complex Script Languages

Alam

Mehmood

Nelson

2015

Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries

View full text Add to dashboard Cite

We propose an approach to index raster images of dictionary pages which in turn would require very little manual effort to enable direct access to the appropriate pages of the dictionary for lookup. Accessibility is further improved by feedback and crowdsourcing that enables highlighting of the specific location on the page where the lookup word is found, annotation, digitization, and fielded searching. This approach is equally applicable on simple scripts as well as complex writing systems. Using our proposed approach, we have built a Web application called "Dictionary Explorer" which supports word indexes in various languages and every language can have multiple dictionaries associated with it. Word lookup gives direct access to appropriate pages of all the dictionaries of that language simultaneously. The application has exploration features like searching, pagination, and navigating the word index through a tree-like interface. The application also supports feedback, annotation, and digitization features. Apart from the scanned images, "Dictionary Explorer" aggregates results from various sources and user contributions in Unicode. We have evaluated the time required for indexing dictionaries of different sizes and complexities in the Urdu language and examined various tradeoffs in our implementation. Using our approach, a single person can make a dictionary of 1,000 pages searchable in less than an hour.

show abstract

On lexical resources for digitization of historical documents

Cited by 14 publications

References 9 publications

Document conversion for cultural heritage texts

Document conversion for cultural heritage texts

New Publication Cultures in the Humanities: Exploring the Paradigm Shift

Improving Accessibility of Archived Raster Dictionaries of Complex Script Languages

Contact Info

Product

Resources

About