Exponential language modeling using morphological features and multi-task learning

For languages with fast vocabulary growth and limited resources, data sparsity leads to challenges in training a language model. One strategy for addressing this problem is to leverage morphological structure as features in the model. This paper explores different uses of unsupervised morphological...

ver descrição completa

Detalhes bibliográficos
Principais autores: Fang, H, Ostendorf, M, Baumann, P, Pierrehumbert, J
Formato: Journal article
Publicado em: Institute of Electrical and Electronics Engineers 2015

Registros relacionados