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