Unsupervised Summarization Re-ranking

by   Mathieu Ravaut, et al.

With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags significantly behind their supervised counterparts. Similarly to the supervised setup, we notice a very high variance in quality among summary candidates from these models whereas only one candidate is kept as the summary output. In this paper, we propose to re-rank summary candidates in an unsupervised manner, aiming to close the performance gap between unsupervised and supervised models. Our approach improves the pre-trained unsupervised PEGASUS by 4.37 summarization benchmarks, and achieves relative gains of 7.51 averaged over 30 transfer setups.


page 1

page 2

page 3

page 4


Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization

Unsupervised document summarization has re-acquired lots of attention in...

Towards Summary Candidates Fusion

Sequence-to-sequence deep neural models fine-tuned for abstractive summa...

Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality

Improving factual consistency of abstractive summarization has been a wi...

Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization

Text summarization aims to generate a short summary for an input text. I...

PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization

Based on the remarkable achievements of pre-trained language models in a...

BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

The principle of the Information Bottleneck (Tishby et al. 1999) is to p...

Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization

The goal of multimodal abstractive summarization (MAS) is to produce a c...

Please sign up or login with your details

Forgot password? Click here to reset