Cross-lingual, Character-Level Neural Morphological Tagging

Ryan Cotterell, Georg Heigold

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.
BibTeX
@inproceedings{cotterell2017cross,
  author = {Ryan Cotterell and Georg Heigold},
  title = {{Cross-lingual, Character-Level Neural Morphological Tagging}},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2017},
  url = {https://openreview.net/forum?id=aq9s706Cj9Q},
}

Loading related content...

Figure