Names, Right or Wrong

Named Entities in an OCRed Historical Finnish Newspaper

Kimmo Tapio Kettunen, Teemu Petteri Ruokolainen

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

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 [16]. 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 evaluation result of NER with data out of a digitized Finnish historical newspaper collection Digi. Experiments, results and discussion of this research serve development of the Web collection of historical Finnish newspapers

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 70–75% [7]. Our baseline NER tagger is a rule-based tagger of Finnish, FiNER, provided by the FIN-CLARIN consortium. Three other available tools are also evaluated: a Finnish Semantic Tagger (FST), Connexor’s NER tool and Polyglot’s NER.
Originalspråkengelska
Titel på gästpublikationProceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage
Antal sidor6
UtgivningsortNew York
FörlagACM
Utgivningsdatum1 jun 2017
Sidor181-186
ISBN (elektroniskt)978-1-4503-5265-9
DOI
StatusPublicerad - 1 jun 2017
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangDaTeCH 2017 - Göttingen, Tyskland
Varaktighet: 1 jun 20172 jun 2017

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här

Kettunen, K. T., & Ruokolainen, T. P. (2017). Names, Right or Wrong: Named Entities in an OCRed Historical Finnish Newspaper. I Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage (s. 181-186). New York: ACM. https://doi.org/10.1145/3078081.3078084
Kettunen, Kimmo Tapio ; Ruokolainen, Teemu Petteri. / Names, Right or Wrong : Named Entities in an OCRed Historical Finnish Newspaper. Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage. New York : ACM, 2017. s. 181-186
@inproceedings{14da84ddb32f4c55982fa94f4445dee1,
title = "Names, Right or Wrong: Named Entities in an OCRed Historical Finnish Newspaper",
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 [16]. 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 evaluation result of NER with data out of a digitized Finnish historical newspaper collection Digi. Experiments, results and discussion of this research serve development of the Web collection of historical Finnish newspapersDigi 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 70–75{\%} [7]. Our baseline NER tagger is a rule-based tagger of Finnish, FiNER, provided by the FIN-CLARIN consortium. Three other available tools are also evaluated: a Finnish Semantic Tagger (FST), Connexor’s NER tool and Polyglot’s NER.",
keywords = "113 Computer and information sciences, named entity recognition",
author = "Kettunen, {Kimmo Tapio} and Ruokolainen, {Teemu Petteri}",
note = "Volume: Proceeding volume:",
year = "2017",
month = "6",
day = "1",
doi = "10.1145/3078081.3078084",
language = "English",
pages = "181--186",
booktitle = "Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage",
publisher = "ACM",
address = "International",

}

Kettunen, KT & Ruokolainen, TP 2017, Names, Right or Wrong: Named Entities in an OCRed Historical Finnish Newspaper. i Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage. ACM, New York, s. 181-186, Göttingen, Tyskland, 01/06/2017. https://doi.org/10.1145/3078081.3078084

Names, Right or Wrong : Named Entities in an OCRed Historical Finnish Newspaper. / Kettunen, Kimmo Tapio; Ruokolainen, Teemu Petteri.

Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage. New York : ACM, 2017. s. 181-186.

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

TY - GEN

T1 - Names, Right or Wrong

T2 - Named Entities in an OCRed Historical Finnish Newspaper

AU - Kettunen, Kimmo Tapio

AU - Ruokolainen, Teemu Petteri

N1 - Volume: Proceeding volume:

PY - 2017/6/1

Y1 - 2017/6/1

N2 - 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 [16]. 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 evaluation result of NER with data out of a digitized Finnish historical newspaper collection Digi. Experiments, results and discussion of this research serve development of the Web collection of historical Finnish newspapersDigi 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 70–75% [7]. Our baseline NER tagger is a rule-based tagger of Finnish, FiNER, provided by the FIN-CLARIN consortium. Three other available tools are also evaluated: a Finnish Semantic Tagger (FST), Connexor’s NER tool and Polyglot’s NER.

AB - 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 [16]. 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 evaluation result of NER with data out of a digitized Finnish historical newspaper collection Digi. Experiments, results and discussion of this research serve development of the Web collection of historical Finnish newspapersDigi 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 70–75% [7]. Our baseline NER tagger is a rule-based tagger of Finnish, FiNER, provided by the FIN-CLARIN consortium. Three other available tools are also evaluated: a Finnish Semantic Tagger (FST), Connexor’s NER tool and Polyglot’s NER.

KW - 113 Computer and information sciences

KW - named entity recognition

U2 - 10.1145/3078081.3078084

DO - 10.1145/3078081.3078084

M3 - Conference contribution

SP - 181

EP - 186

BT - Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage

PB - ACM

CY - New York

ER -

Kettunen KT, Ruokolainen TP. Names, Right or Wrong: Named Entities in an OCRed Historical Finnish Newspaper. I Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage. New York: ACM. 2017. s. 181-186 https://doi.org/10.1145/3078081.3078084