Self-Supervised Learning for Contextualized Extractive Summarization

Code

• github.com/hongwang600/Summarization
  OfficialIn paperpytorch★ 0
• github.com/minsoo9506/NLP-study
  pytorch★ 0

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.

Tasks

Reproductions