论文信息 - A Memory-Based Tagger for Polish

A Memory-Based Tagger for Polish

We present and evaluate a tiered memory-based tagger for Polish. The tagger is tested on two manually annotated corpora and achieves state-of-the-art results. We also show that the tagger used in a simple voting ensemble allows to achieve a significant increase in accuracy as compared to previous experiements in voting.

Adam Radziszewski | Tomasz Śniatowski

[1] Szymon Acedanski,et al. A Morphosyntactic Brill Tagger for Inflectional Languages , 2010, IceTAL.

[2] Adam Przepiórkowski,et al. Towards the Adequate Evaluation of Morphosyntactic Taggers , 2010, COLING.

[3] Walter Daelemans,et al. Memory-Based Language Processing , 2009, Studies in natural language processing.

[4] Helmut Schmid,et al. Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging , 2008, COLING.

[5] Eric Brill,et al. A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[6] Maciej Piasecki,et al. Combining Polish Morphosyntactic Taggers , 2011, SIIS.

[7] Adam Radziszewski,et al. WCCL: A Morpho-syntactic Feature Toolkit , 2011, TSD.

[8] Adam Radziszewski,et al. Maca — a configurable tool to integrate Polish morphological data , 2011 .

[9] Dan Tufis. Tiered Tagging and Combined Language Models Classifiers , 1999, TSD.

[10] Adam Przepiórkowski,et al. A Flexemic Tagset for Polish , 2003 .

[11] M. Piasecki,et al. Polish tagger TaKIPI: rule based construction and optimization , 2007 .