Search for: All records

This paper introduces our Diversity Advanced Actor-Critic reinforcement learning (A2C) framework (DAAC) to improve the generalization and accuracy of Natural Language Processing (NLP). We show that the diversification of training samples alleviates overfitting and improves model generalization and accuracy. We quantify diversity on a set of samples using the max dispersion, convex hull volume, and graph entropy based on sentence embeddings in high-dimensional metric space. We also introduce A2C to select such a diversified training subset efficiently. Our experiments achieve up to +23.8 accuracy increase (38.0{\%} relatively) in sentiment analysis, -44.7 perplexity decrease (37.9{\%} relatively) in language modeling, and consistent improvements in named entity recognition over various domains. In particular, our method outperforms both domain adaptation and generalization baselines without using any target domain knowledge.