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...

תיאור מלא

מידע ביבליוגרפי
Main Authors: Fang, H, Ostendorf, M, Baumann, P, Pierrehumbert, J
פורמט: Journal article
יצא לאור: Institute of Electrical and Electronics Engineers 2015