Deep Transfer Reinforcement Learning for Text Summarization
TL
TL;DR
This work proposes 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 and provides a generic solution that works well on unseen data.
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.
References37 items
1
Neural Abstractive Text Summarization with Sequence-to-Sequence Models
2
Neural Adaptation Layers for Cross-domain Named Entity Recognition
3
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization
4
Improving Abstraction in Text Summarization
5