Combining Phonology and Morphology for the Normalization of Historical Texts
Izaskun Etxeberria, Iñaki Alegria, Larraitz Uria, Mans Hulden · 2016
This paper presents a proposal for the normalization of word-forms in historical texts.To perform this task, we extend our previous research on induction of phonology and adapt it to the task of normalization.In particular, we combine our earlier models with models for learning morphology (without additional supervision).The results are mixed: induction of the segmentation of morphemes fails to directly offer significant improvements while including known morpheme boundaries in standard texts do improve results.