Meta-Transfer Learning for Low-Resource Abstractive Summarization

Authors

  • Yi-Syuan Chen National Chiao Tung University
  • Hong-Han Shuai National Chiao Tung University

Keywords:

Summarization, Transfer/Adaptation/Multi-task/Meta/Automated Learning

Abstract

Neural abstractive summarization has been studied in many pieces of literature and achieves great success with the aid of large corpora. However, when encountering novel tasks, one may not always benefit from transfer learning due to the domain shifting problem, and overfitting could happen without adequate labeled examples. Furthermore, the annotations of abstractive summarization are costly, which often demand domain knowledge to ensure the ground-truth quality. Thus, there are growing appeals for Low-Resource Abstractive Summarization, which aims to leverage past experience to improve the performance with limited labeled examples of target corpus. In this paper, we propose to utilize two knowledge-rich sources to tackle this problem, which are large pre-trained models and diverse existing corpora. The former can provide the primary ability to tackle summarization tasks; the latter can help discover common syntactic or semantic information to improve the generalization ability. We conduct extensive experiments on various summarization corpora with different writing styles and forms. The results demonstrate that our approach achieves the state-of-the-art on 6 corpora in low-resource scenarios, with only 0.7% of trainable parameters compared to previous work.

Downloads

Published

2021-05-18

How to Cite

Chen, Y.-S., & Shuai, H.-H. (2021). Meta-Transfer Learning for Low-Resource Abstractive Summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12692-12700. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17503

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I