论文信息 - Tagging Icelandic Text using a Linguistic and a Statistical Tagger

Tagging Icelandic Text using a Linguistic and a Statistical Tagger

We describe our linguistic rule-based tagger IceTagger, and compare its tagging accuracy to the TnT tagger, a state-of-the-art statistical tagger, when tagging Icelandic, a morphologically complex language. Evaluation shows that the average tagging accuracy is 91.54% and 90.44%, obtained by IceTagger and TnT, respectively. When tag profile gaps in the lexicon, used by the TnT tagger, are filled with tags produced by our morphological analyser IceMorphy, TnT's tagging accuracy increases to 91.18%.

Hrafn Loftsson | H. Loftsson

[1] Atro Voutilainen. A syntax-based part-of-speech analyser , 1995, EACL.

[2] Atro Voutilainen,et al. Comparing a Linguistic and a Stochastic Tagger , 1997, ACL.

[3] Preslav Nakov,et al. Guessing morphological classes of unknown German nouns , 2003, RANLP.

[4] Eiríkur Rögnvaldsson,et al. Testing Data-Driven Learning Algorithms for PoS Tagging of Icelandic , 2007 .

[5] Hrafn Loftsson,et al. Tagging a Morphologically Complex Language Using Heuristics , 2006, FinTAL.

[6] Hrafn Loftsson,et al. Tagging Icelandic text: A linguistic rule-based approach , 2008, Nordic Journal of Linguistics.

[7] Atro Voutilainen,et al. A language-independent system for parsing unrestricted text , 1995 .

[8] Hrafn Loftsson,et al. Tagging Icelandic text: an experiment with integrations and combinations of taggers , 2007, Lang. Resour. Evaluation.

[9] Andrei Mikheev,et al. Automatic Rule Induction for Unknown-Word Guessing , 1997, CL.

[10] Thorsten Brants,et al. TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.