English

Self-Supervised Learning for Contextualized Extractive Summarization

Computation and Language 2019-06-12 v1

Abstract

Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing three auxiliary pre-training tasks that learn to capture the document-level context in a self-supervised fashion. Experiments on the widely-used CNN/DM dataset validate the effectiveness of the proposed auxiliary tasks. Furthermore, we show that after pre-training, a clean model with simple building blocks is able to outperform previous state-of-the-art that are carefully designed.

Keywords

Cite

@article{arxiv.1906.04466,
  title  = {Self-Supervised Learning for Contextualized Extractive Summarization},
  author = {Hong Wang and Xin Wang and Wenhan Xiong and Mo Yu and Xiaoxiao Guo and Shiyu Chang and William Yang Wang},
  journal= {arXiv preprint arXiv:1906.04466},
  year   = {2019}
}

Comments

Accepted to ACL 2019

R2 v1 2026-06-23T09:49:54.544Z