| Publikationstyp: | Konferenz: Paper |
| Art der Begutachtung: | Peer review (Abstract) |
| Titel: | Manual and semi-automatic normalization of historical spelling : case studies from Early New High German |
| Autor/-in: | Bollmann, Marcel Dipper, Stefanie Krasselt, Julia Petran, Florian |
| Tagungsband: | Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012 |
| Seite(n): | 342 |
| Seiten bis: | 350 |
| Angaben zur Konferenz: | Conference on Natural Language Processing (KONVENS 2012), Vienna, Austria, 21 September 2012 |
| Erscheinungsdatum: | 2012 |
| Reihe: | Schriftenreihe der Österreichischen Gesellschaft für Artificial Intelligence (ÖGAI) |
| Reihenzählung: | 5 |
| Verlag / Hrsg. Institution: | Eigenverlag ÖGAI |
| Verlag / Hrsg. Institution: | Wien |
| ISBN: | 3-85027-005-X |
| Sprache: | Englisch |
| Fachgebiet (DDC): | 410.285: Computerlinguistik |
| Zusammenfassung: | This paper presents work on manual and semi-automatic normalization of historical language data. We first address the guidelines that we use for mapping historical to modern word forms. The guidelines distinguish between normalization (preferring forms close to the original) and modernization (preferring forms close to modern language). Average inter-annotator agreement is 88.38% on a set of data from Early New High German. We then present Norma, a semi-automatic normalization tool. It integrates different modules (lexicon lookup, rewrite rules) for normalizing words in an interactive way. The tool dynamically updates the set of rule entries, given new input. Depending on the text and training settings, normalizing 1,000 tokens results in overall accuracies of 61.78–79.65% (baseline: 24.76–59.53%). |
| URI: | http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf https://digitalcollection.zhaw.ch/handle/11475/4045 |
| Volltext Version: | Publizierte Version |
| Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
| Departement: | Angewandte Linguistik |
| Enthalten in den Sammlungen: | Publikationen Angewandte Linguistik |
Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige
Bollmann, M., Dipper, S., Krasselt, J., & Petran, F. (2012). Manual and semi-automatic normalization of historical spelling : case studies from Early New High German [Conference paper]. Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012, 342–350. http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf
Bollmann, M. et al. (2012) ‘Manual and semi-automatic normalization of historical spelling : case studies from Early New High German’, in Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012. Wien: Eigenverlag ÖGAI, pp. 342–350. Available at: http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf.
M. Bollmann, S. Dipper, J. Krasselt, and F. Petran, “Manual and semi-automatic normalization of historical spelling : case studies from Early New High German,” in Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012, 2012, pp. 342–350. [Online]. Available: http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf
BOLLMANN, Marcel, Stefanie DIPPER, Julia KRASSELT und Florian PETRAN, 2012. Manual and semi-automatic normalization of historical spelling : case studies from Early New High German. In: Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012 [online]. Conference paper. Wien: Eigenverlag ÖGAI. 2012. S. 342–350. ISBN 3-85027-005-X. Verfügbar unter: http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf
Bollmann, Marcel, Stefanie Dipper, Julia Krasselt, and Florian Petran. 2012. “Manual and Semi-Automatic Normalization of Historical Spelling : Case Studies from Early New High German.” Conference paper. In Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012, 342–50. Wien: Eigenverlag ÖGAI. http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf.
Bollmann, Marcel, et al. “Manual and Semi-Automatic Normalization of Historical Spelling : Case Studies from Early New High German.” Proceedings of the 11th Edition of the Conference on Natural Language Processing (KONVENS). Vienna, September 19-21, 2012, Eigenverlag ÖGAI, 2012, pp. 342–50, http://www.oegai.at/konvens2012/proceedings/51_bollmann12w/51_bollmann12w.pdf.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.