Assigning Fine-grained PoS Tags based on High-precision Coarse-grained Tagging

Tobias Horsmann, Torsten Zesch


Abstract
We propose a new approach to PoS tagging where in a first step, we assign a coarse-grained tag corresponding to the main syntactic category. Based on this high-precision decision, in the second step we utilize specially trained fine-grained models with heavily reduced decision complexity. By analyzing the system under oracle conditions, we show that there is a quite large potential for significantly outperforming a competitive baseline. When we take error-propagation from the coarse-grained tagging into account, our approach is on par with the state of the art. Our approach also allows tailoring the tagger towards recognizing single word classes which are of interest e.g. for researchers searching for specific phenomena in large corpora. In a case study, we significantly outperform a standard model that also makes use of the same optimizations.
Anthology ID:
C16-1032
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
328–336
Language:
URL:
https://aclanthology.org/C16-1032
DOI:
Bibkey:
Cite (ACL):
Tobias Horsmann and Torsten Zesch. 2016. Assigning Fine-grained PoS Tags based on High-precision Coarse-grained Tagging. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 328–336, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Assigning Fine-grained PoS Tags based on High-precision Coarse-grained Tagging (Horsmann & Zesch, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1032.pdf
Data
Penn Treebank