Learning to Learn Morphological Inflection for Resource-Poor Languages

Authors

  • Katharina Kann New York University
  • Samuel R. Bowman New York University
  • Kyunghyun Cho New York University

DOI:

https://doi.org/10.1609/aaai.v34i05.6316

Abstract

We propose to cast the task of morphological inflection—mapping a lemma to an indicated inflected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.

Downloads

Published

2020-04-03

How to Cite

Kann, K., Bowman, S. R., & Cho, K. (2020). Learning to Learn Morphological Inflection for Resource-Poor Languages. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8058-8065. https://doi.org/10.1609/aaai.v34i05.6316

Issue

Section

AAAI Technical Track: Natural Language Processing