Deep Transfer Reinforcement Learning for Text Summarization

TL;DR

This paper introduces a reinforcement learning framework for transfer learning in text summarization, enabling models to generalize better across datasets and perform well with limited training data.

Contribution

It presents the first study of transfer learning in text summarization and proposes a generic reinforcement learning approach that improves generalization and data efficiency.

Findings

Achieves state-of-the-art results on multiple datasets.

Demonstrates effective fine-tuning with few samples.

Shows improved generalization to unseen datasets.

Abstract

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.