Abstract
In this paper, we experiment with using Stagger, an open-source implementation of an Averaged Perceptron tagger, to tag Icelandic, a morphologically complex language. By adding language specific linguistic features and using IceMorphy, an unknown word guesser, we obtain state-of-the-art tagging accuracy of 92.82%. Furthermore, by adding data from a morphological database, and word embeddings induced from an unannotated corpus, the accuracy increases to 93.84%. This is equivalent to an error reduction of 5.5%, compared to the previously best tagger for Icelandic, consisting of linguistic rules and a Hidden Markov Model.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013) |
| Place of Publication | Oslo, Norway |
| Publisher | Linköping University Electronic Press, Sweden |
| Pages | 105-119 |
| Number of pages | 15 |
| Publication status | Published - 1 May 2013 |