How to do lexical quality estimation of a large OCRed historical Finnish newspaper collection with scarce resources

TL;DR

This paper evaluates methods for estimating the lexical quality of a large OCRed Finnish newspaper collection with limited resources, combining corpus analysis, morphological tools, and error rate comparisons.

Contribution

It introduces a multi-method approach for assessing OCR quality in large historical collections, tailored for resource-scarce scenarios.

Findings

Parallel sample analysis and word error rates provide useful quality estimates.

Morphological analyzers help identify lexical inconsistencies.

Frequency analysis and comparison to edited data reveal collection quality.

Abstract

The National Library of Finland has digitized the historical newspapers published in Finland between 1771 and 1910. This collection contains approximately 1.95 million pages in Finnish and Swedish. Finnish part of the collection consists of about 2.40 billion words. The National Library's Digital Collections are offered via the digi.kansalliskirjasto.fi web service, also known as Digi. Part of the newspaper material (from 1771 to 1874) is also available freely downloadable in The Language Bank of Finland provided by the FINCLARIN consortium. The collection can also be accessed through the Korp environment that has been developed by Spr{\aa}kbanken at the University of Gothenburg and extended by FINCLARIN team at the University of Helsinki to provide concordances of text resources. A Cranfield style information retrieval test collection has also been produced out of a small part of the Digi newspaper material at the University of Tampere. Quality of OCRed collections is an important topic in digital humanities, as it affects general usability and searchability of collections. There is no single available method to assess quality of large collections, but different methods can be used to approximate quality. This paper discusses different corpus analysis style methods to approximate overall lexical quality of the Finnish part of the Digi collection. Methods include usage of parallel samples and word error rates, usage of morphological analyzers, frequency analysis of words and comparisons to comparable edited lexical data. Our aim in the quality analysis is twofold: firstly to analyze the present state of the lexical data and secondly, to establish a set of assessment methods that build up a compact procedure for quality assessment after e.g. new OCRing or post correction of the material. In the discussion part of the paper we shall synthesize results of our different analyses.