TY  - INPR
A1  - Ivanova, Steliana
A1  - Kübler, Sandra
A2  - Calzolari, Nicoletta
A2  - Choukri, Khalid
A2  - Maegaard, Bente
A2  - Mariani, Joseph
A2  - Odijk, Jan
A2  - Piperidis, Stelios
A2  - Tapias, Daniel
T1  - POS tagging for German : how important is the right context?
N2  - 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%.
KW  - Tagging
KW  - Acquisition
KW  - Machine Learning
Y1  - 2008
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/9887
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30-1110660
UR  - http://cl.indiana.edu/~skuebler/papers/postagging.pdf
SN  - 2-9517408-4-0
SN  - 2522-2686
N1  - 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
ER  -