Deep Transfer Reinforcement Learning for Text Summarization
This addresses the data-hungry nature of deep learning for text summarization, offering a transfer learning solution that improves generalization to unseen datasets, though it appears incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of training deep neural networks for text summarization on small datasets by proposing a reinforcement learning framework, which achieves state-of-the-art results and good generalization across various datasets, with the ability to fine-tune using only a few samples.
Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such as image analysis. In this paper, we study the problem of transfer learning for text summarization and discuss why existing state-of-the-art models fail to generalize well on other (unseen) datasets. We propose a reinforcement learning framework based on a self-critic policy gradient approach which achieves good generalization and state-of-the-art results on a variety of datasets. Through an extensive set of experiments, we also show the ability of our proposed framework to fine-tune the text summarization model using only a few training samples. To the best of our knowledge, this is the first work that studies transfer learning in text summarization and provides a generic solution that works well on unseen data.