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...

詳細記述

書誌詳細
主要な著者: Fang, H, Ostendorf, M, Baumann, P, Pierrehumbert, J
フォーマット: Journal article
出版事項: Institute of Electrical and Electronics Engineers 2015