A Hybrid Morphological Disambiguation System for Turkish
Mücahid Kutlu, Ilyas Cicekli · International Joint Conference on Natural Language Processing · 2013
In this paper, we propose a morphological disambiguation method for Turkish, which is an agglutinative language. We use a hybrid method, which combines statistical information with handcrafted rules and learned rules. Five different steps are applied for disambiguation. In the first step, the most likely tags of words are selected. In the second step, we use handcrafted rules to constrain possible parses or select the correct parse. Next, the most likely tags are selected for still ambiguous words according to the suffixes of the words that are unseen in the training corpus. Then, we use transformation-based rules that are learned by a variation of Brill tagger. If the word is still ambiguous, we use some heuristics for the disambiguation. We constructed a hand-tagged dataset for training and applied a ten-fold cross validation with this dataset. We obtained 93.4% accuracy on the average when whole morphological parses are considered in calculation. The accuracy increased to 94.1% when only part-of-speech tags and inflections of last derivations are considered. Our accuracy is 96.9% in terms of part-of-speech tagging.