Romanian is known for having a rich inflectional morphology due to the multitude of
inflectional ending categories as well as due to stem alternations (apophony). This richness …

Abstract The use of Deep Neural Network architectures for Language Modelling has recently
seen a tremendous increase in interest in the field of NLP with the advent of transfer learning …

In this paper we present a deep learning architecture capable of predicting the full
inflectional paradigms from the uninflected, dictionary form of a word and the full …

Sub-word level alternations during inflection (apophonies) are an common linguistic
phenomenon present in morphologically-rich languages, like Romanian. Inflection learning …

The use of Deep Neural Network architectures for Language Modeling has recently seen a
tremendous increase in interest in the field of NLP with the advent of transfer learning and …