On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
Computation and Language
2020-04-29 v2
Abstract
We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarization. We perform a simple extractive step before generating a summary, which is then used to condition the transformer language model on relevant information before being tasked with generating a summary. We show that this extractive step significantly improves summarization results. We also show that this approach produces more abstractive summaries compared to prior work that employs a copy mechanism while still achieving higher rouge scores. Note: The abstract above was not written by the authors, it was generated by one of the models presented in this paper.
Cite
@article{arxiv.1909.03186,
title = {On Extractive and Abstractive Neural Document Summarization with Transformer Language Models},
author = {Sandeep Subramanian and Raymond Li and Jonathan Pilault and Christopher Pal},
journal= {arXiv preprint arXiv:1909.03186},
year = {2020}
}