Neural Networks for Morphological Generation in the Minimal-Resource Setting

ABSTRACT: As languages other than English are moving more and more into the focus of natural language processing, accurate handling of morphology is increasing in importance. This talk presents neural network-based approaches to morphological generation, casting the problem as a character-based sequence-to-sequence task. First, we will generally discuss how to successfully train neural sequence-to-sequence models for this. Then, since many morphologically rich languages are low-resource, the main part of the talk will focus on how to overcome the challenges that limited amounts of annotated training data pose to neural models. The approaches covered in this talk include multi-task learning, cross-lingual transfer learning, and meta-learning.

BIO: Katharina Kann is a postdoc working with Sam Bowman and Kyunghyun Cho at NYU in New York. Before that, she was a PhD student under the supervision of Hinrich Schütze at LMU Munich. The main focus of her research lies on deep learning for natural language processing. In particular, she is interested in morphology and approaches for the low-resource setting. She won the SIGMORPHON 2016 shared task on morphological reinflection.