Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages

Katharina Kann, Manuel Mager, Ivan Meza, Hinrich Schütze


Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of the art for morphological segmentation in high-resource settings and for (mostly) European languages, we first show that they also obtain competitive performance for Mexican polysynthetic languages in minimal-resource settings. We then propose two novel multi-task training approaches -one with, one without need for external unlabeled resources-, and two corresponding data augmentation methods, improving over the neural baseline for all languages. Finally, we explore cross-lingual transfer as a third way to fortify our neural model and show that we can train one single multi-lingual model for related languages while maintaining comparable or even improved performance, thus reducing the amount of parameters by close to 75%. We provide our morphological segmentation datasets for Mexicanero, Nahuatl, Wixarika and Yorem Nokki for future research.



You are welcome to use the code and datasets, however please acknowledge its use with a citation:
author = {Kann, Katharina and Mager, Manuel and Meza, Ivan and Sch\"{u}tze, Hinrich},
title = {Fortification of Neural Morphological Segmentation Models 
for Polysynthetic Minimal-Resource Languages},
booktitle = {Proceedings of NAACL 2018} ,
month = {June},
year = {2018},
address = {New Orleans, Louisiana, USA},
publisher = {Association for Computational Linguistics},