POS tagging for German : how important is the right context?
- Part-of-Speech tagging is generally performed by Markov models, based on bigram or trigram models. While Markov models have a strong concentration on the left context of a word, many languages require the inclusion of right context for correct disambiguation. We show for German that the best results are reached by a combination of left and right context. If only left context is available, then changing the direction of analysis and going from right to left improves the results. In a version of MBT (Daelemans et al., 1996) with default parameter settings, the inclusion of the right context improved POS tagging accuracy from 94.00% to 96.08%, thus corroborating our hypothesis. The version with optimized parameters reaches 96.73%.
Download full text files
Additional Services
| Author: | Steliana Ivanova, Sandra KüblerORCiDGND |
|---|---|
| URN: | urn:nbn:de:hebis:30-1110660 |
| URL: | http://cl.indiana.edu/~skuebler/papers/postagging.pdf |
| ISBN: | 2-9517408-4-0 |
| ISSN: | 2522-2686 |
| Editor: | Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias |
| Document Type: | Preprint |
| Language: | German |
| Year of Completion: | 2008 |
| Year of first Publication: | 2008 |
| Publishing Institution: | Universitätsbibliothek Johann Christian Senckenberg |
| Release Date: | 2008/10/21 |
| Tag: | Acquisition; Machine Learning; Tagging |
| Page Number: | 4 |
| Note: | Erschienen in: Nicoletta Calzolari ; Khalid Choukri ; Bente Maegaard ; Joseph Mariani ; Jan Odijk ; Stelios Piperidis ; Daniel Tapias (Hrsg.): Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC-2008), May, 28-30, 2008. Marrakech, Marocco, Paris : ELRA, 2008, S. 994-997, ISBN: 2-9517408-4-0 |
| Source: | http://jones.ling.indiana.edu/~skuebler/papers/postagging.pdf ; (in:) Proceedings of the Sixth International Conference on Language Resources and Evaluation, LREC 2007 - Marrakesh, 2008. |
| HeBIS-PPN: | 205688187 |
| Institutes: | keine Angabe Fachbereich / Extern |
| Dewey Decimal Classification: | 4 Sprache / 40 Sprache / 400 Sprache |
| Sammlungen: | Linguistik |
| Linguistik-Klassifikation: | Linguistik-Klassifikation: Computerlinguistik / Computational linguistics |
| Licence (German): |  Deutsches Urheberrecht |
