Cross-lingual, Character-Level Neural Morphological Tagging
Computation and Language
2025-04-25 v6
Abstract
Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model.
Cite
@article{arxiv.1708.09157,
title = {Cross-lingual, Character-Level Neural Morphological Tagging},
author = {Ryan Cotterell and Georg Heigold},
journal= {arXiv preprint arXiv:1708.09157},
year = {2025}
}
Comments
Published as a conference paper at EMNLP 2017; Fixed minor typos and cleaned up formatting