Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models
Huiming Jin, Katharina Kann · 2017
Multi-task training is an effective method to mitigate the data sparsity problem.It has recently been applied for crosslingual transfer learning for paradigm completion-the task of producing inflected forms of lemmata-with sequenceto-sequence networks.However, it is still vague how the model transfers knowledge across languages, as well as if and which information is shared.To investigate this, we propose a set of data-dependent experiments using an existing encoder-decoder recurrent neural network for the task.Our results show that indeed the performance gains surpass a pure regularization effect and that knowledge about language and morphology can be transferred.