A Comparative Study on Regularization Strategies for Embedding-based Neural Networks
This work addresses overfitting issues in NLP models, but it is incremental as it focuses on comparing existing methods.
The paper compared various regularization strategies to combat severe overfitting in embedding-based neural networks for NLP, finding that incremental hyperparameter tuning and combining regularizations improved model performance.
This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried several frequently applied or newly proposed regularization strategies, including penalizing weights (embeddings excluded), penalizing embeddings, re-embedding words, and dropout. We also emphasized on incremental hyperparameter tuning, and combining different regularizations. The results provide a picture on tuning hyperparameters for neural NLP models.