Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning
This work addresses the challenge of enhancing task-specific word embeddings for NLP applications, representing an incremental improvement over existing curriculum learning methods.
The paper tackles the problem of improving word representation learning by using Bayesian optimization to learn curricula that optimize performance on downstream tasks, showing that this approach outperforms random orders and natural corpus order.
We use Bayesian optimization to learn curricula for word representation learning, optimizing performance on downstream tasks that depend on the learned representations as features. The curricula are modeled by a linear ranking function which is the scalar product of a learned weight vector and an engineered feature vector that characterizes the different aspects of the complexity of each instance in the training corpus. We show that learning the curriculum improves performance on a variety of downstream tasks over random orders and in comparison to the natural corpus order.