POS-Tagging Historical Corpora: The Case of Early New High German
- A key problem in automatic annotation of historical corpora is inconsistent spelling. Because the spelling of some word forms can differ between texts, a language model trained on already annotated treebanks may fail to recognize known word forms due to differences in spelling. In the present work, we explore the feasibility of an unsupervised method for spelling-adjustment for the purpose of improved part of speech (POS) tagging. To this end, we present a method for spelling normalization based on weighted edit distances, which exploits within-text spelling variation. We then evaluate the improvement in taging accuracy resulting from between-texts spelling normalization in two tagging experiments on several Early New High German (ENHG) texts.
Weitere Dienste
| Verfasserangaben: | Ulrike DemskeORCiDGND, Pavel LogacevORCiDGND, Katrin Goldschmidt |
|---|---|
| Titel des übergeordneten Werks (Englisch): | Proceedings of the thirteenth workshop on treebanks and linguistic theories (TLT 13) |
| Verlag: | TALAR - Tübingen Archive of Language Resources |
| Verlagsort: | Tübingen |
| Publikationstyp: | Konferenzveröffentlichung |
| Sprache: | Englisch |
| Datum der Erstveröffentlichung: | 13.12.2014 |
| Erscheinungsjahr: | 2014 |
| Veröffentlichende Institution: | Universität Potsdam |
| Datum der Freischaltung: | 04.02.2020 |
| Band: | 2014 |
| Seitenanzahl: | 10 |
| Erste Seite: | 103 |
| Letzte Seite: | 112 |
| Organisationseinheiten: | Philosophische Fakultät / Institut für Germanistik |
| DDC-Klassifikation: | 4 Sprache / 41 Linguistik / 415 Grammatik |
