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...
| Autors principals: | , , , |
|---|---|
| Format: | Journal article |
| Publicat: |
Institute of Electrical and Electronics Engineers
2015
|