North Sámi morphological segmentation with low-resource semi-supervised sequence labeling
Conference article in proceedings
Fifth Workshop on Computational Linguistics for Uralic Languages
AbstractSemi-supervised sequence labeling is an effective way to train a low-resource morphological segmentation system. We show that a feature set augmentation approach, which combines the strengths of generative and discriminative mod- els, is suitable both for graphical models like conditional random field (CRF) and sequence-to-sequence neural models. We perform a comparative evaluation be- tween three existing and one novel semi-supervised segmentation methods. All four systems are language-independent and have open-source implementations. We improve on previous best results for North Sámi morphological segmentation. We see a relative improvement in morph boundary F 1 -score of 8.6% compared to using the generative Morfessor FlatCat model directly and 2.4% compared to a seq2seq baseline. Our neural sequence tagging system reaches almost the same performance as the CRF topline.
| openaire: EC/H2020/780069/EU//MeMAD
morphology, segmentation, low-resource settings, semi-supervised learning, sequence labeling, recurrent neural networks, conditional random fields, north sami
Grönroos , S-A , Virpioja , S & Kurimo , M 2019 , North Sámi morphological segmentation with low-resource semi-supervised sequence labeling . in Fifth Workshop on Computational Linguistics for Uralic Languages : Proceedings of the Workshop . Association for Computational Linguistics , pp. 15-26 , International Workshop on Computational Linguistics for Uralic Languages , Tartu , Estonia , 07/01/2019 . < https://www.aclweb.org/anthology/W19-0302/ >