@inproceedings{kettunen-et-al-histner2016,
  author =   {Kimmo Kettunen and Eetu Mäkelä and Juha Kuokkala and Teemu Ruokolainen and Jyrki Niemi},
  title =    {Modern Tools for Old Content - in Search of Named Entities in a Finnish OCRed Historical Newspaper Collection 1771-1910},
  booktitle = {Proceedings of LWDA 2016},
  year = {2016},
  month = {September},
  location = {Potsdam, Germany},
  abstract = {Named entity recognition (NER), search, classification and tagging
  of names and name like frequent informational elements in texts, has become a
  standard information extraction procedure for textual data. NER has been applied
  to many types of texts and different types of entities: newspapers, fiction,
  historical records, persons, locations, chemical compounds, protein families, animals
  etc. In general a NER system’s performance is genre and domain dependent
  and also used entity categories vary. The most general set of named entities
  is usually some version of three partite categorization of locations, persons
  and organizations. In this paper we report first trials and evaluation of NER
  with data out of a digitized Finnish historical newspaper collection Digi. Digi
  collection contains 1 960 921 pages of newspaper material from years 1771–
  1910 both in Finnish and Swedish. We use only material of Finnish documents
  in our evaluation. The OCRed newspaper collection has lots of OCR errors; its
  estimated word level correctness is about 74–75 %. Our principal NER tagger
  is a rule-based tagger of Finnish, FiNER, provided by the FIN-CLARIN
  consortium. We show also results of limited category semantic tagging with
  tools of the Semantic Computing Research Group (SeCo) of the Aalto University.
  FiNER is able to achieve up to 60.0 F-score with named entities in the evaluation
  data. Seco’s tools achieve 30.0–60.0 F-score with locations and persons.
  Performance of FiNER and SeCo’s tools with the data shows that at best about
  half of named entities can be recognized even in a quite erroneous OCRed text},
  OPTannotate = {digital humanities, named entity recognition, OCR, historical newspapers},
  OPTproject =  {http://www.seco.hut.fi/projects/viscera/ http://www.seco.hut.fi/projects/dcert/} 
}