Summary Refinement through Denoising

Nikola I. Nikolov, Alessandro Calmanovici, Richard Hahnloser


Abstract
We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting models to correct information redundancy errors that may arise during summarization. We train on synthetically generated noisy summaries, testing three different types of noise that introduce out-of-context information within each summary. When applied on top of extractive and abstractive summarization baselines, our summary denoising models yield metric improvements while reducing redundancy.
Anthology ID:
R19-1097
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
837–843
Language:
URL:
https://www.aclweb.org/anthology/R19-1097
DOI:
10.26615/978-954-452-056-4_097
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/R19-1097.pdf