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...
Үндсэн зохиолчид: | Fang, H, Ostendorf, M, Baumann, P, Pierrehumbert, J |
---|---|
Формат: | Journal article |
Хэвлэсэн: |
Institute of Electrical and Electronics Engineers
2015
|
Ижил төстэй зүйлс
-
Using pronunciation-based morphological subword units to improve OOV handling in keyword search
-н: He, Y, зэрэг
Хэвлэсэн: (2015) -
Binary Classification with a Pseudo Exponential Model and Its Application for Multi-Task Learning
-н: Takashi Takenouchi, зэрэг
Хэвлэсэн: (2015-08-01) -
DagoBERT: generating derivational morphology with a pretrained language model
-н: Hofmann, V, зэрэг
Хэвлэсэн: (2020) -
Subword-based modeling for handling OOV words inkeyword spotting
-н: Yanzhang, H, зэрэг
Хэвлэсэн: (2014) -
Exploring a radically new exponential Retinex model for multi-task environments
-н: Ziaur Rahman, зэрэг
Хэвлэсэн: (2023-07-01)