Open AccessBootstrapping a Neural Morphological Generator from Morphological Analyzer Output for Inuktitut
Author(s) -
Jeffrey Micher
Publication year - 2019
Language(s) - English
DOI - 10.33011/computel.v2i.455
Subject(s) - morpheme , bootstrapping (finance) , context (archaeology) , sequence (biology) , computer science , alternation (linguistics) , artificial neural network , speech recognition , generator (circuit theory) , spectrum analyzer , set (abstract data type) , artificial intelligence , mathematics , linguistics , history , power (physics) , physics , biology , programming language , telecommunications , philosophy , genetics , archaeology , quantum mechanics , econometrics
We present a method for building a morphological generator from the output of an existing analyzer for Inuktitut, in the absence of a two-way finite state transducer which would normally provide this functionality. We make use of a sequence to sequence neural network which “translates” underlying Inuktitut morpheme sequences into surface character sequences. The neural network uses only the previous and the following morphemes as context. We report a morpheme accuracy of approximately 86%. We are able to increase this accuracy slightly by passing deep morphemes directly to output for unknown morphemes. We do not see significant improvement when increasing training data set size, and postulate possible causes for this.