Self-Supervised Learning for Contextualized Extractive Summarization [article]

Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang
2019 arXiv   pre-print
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
more » ... ing, a clean model with simple building blocks is able to outperform previous state-of-the-art that are carefully designed.
arXiv:1906.04466v1 fatcat:qiwejln6vvetzpvsucejtyvzbi