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 languagespecific 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.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:su-90304 |
| Date | January 2013 |
| Creators | Östling, Robert |
| Publisher | Stockholms universitet, Avdelningen för datorlingvistik, Linköping University Electronic Press, Linköpings universitet |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Conference paper, info:eu-repo/semantics/conferenceObject, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | Linköping Electronic Conference Proceedings, 1650-3740, Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013), p. 105-119 |
Page generated in 0.0014 seconds