The CoNLL--SIGMORPHON 2018 shared task on supervised learning of morphological
generation featured data sets from 103 typologically diverse languages. Apart from …

Automatic morphological processing can aid downstream natural language processing
applications, especially for low-resource languages, and assist language documentation …

Neural network approaches have been applied to computational morphology with great
success, improving the performance of most tasks by a large margin and providing new …

Backtranslation is a common technique for leveraging unlabeled data in low-resource
scenarios in machine translation. The method is directly applicable to morphological …

Neural encoder-decoder models are usually applied to morphology learning as an end-
toend process without considering the underlying phonological representations that linguists …

At least 40% of the world's 7000+ languages are believed to be in danger of disappearing
from human use by the end of this century. Many languages will disappear with almost no …

Linguistically faithful and accurate computational analysis of lower levels of language
structure remains relevant, with a wide range of applications, despite the growing interest in …

During this time of heightened interest in computational methods for low-resource
languages an important question needs to explored: What [computational] methods... can …

Most human languages use inflection to express different grammatical meanings like case,
person, number, gender, tense, aspect etc. How to generate the correct inflected forms is an …