Approximate unsupervised summary optimisation for selections of ROUGE

Natalie Schluter, Héctor Martínez Alonso


Abstract
Approximate summary optimisation for selections of ROUGE It is standard to measure automatic summariser performance using the ROUGE metric. Unfortunately, ROUGE is not appropriate for unsupervised summarisation approaches. On the other hand, we show that it is possible to optimise approximately for ROUGE-n by using a document-weighted ROUGE objective. Doing so results in state-of-the-art summariser performance for single and multiple document summaries for both English and French. This is despite a non-correlation of the documentweighted ROUGE metric with human judgments, unlike the original ROUGE metric. These findings suggest a theoretical approximation link between the two metrics.
Anthology ID:
2016.jeptalnrecital-poster.5
Volume:
Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 2 : TALN (Posters)
Month:
7
Year:
2016
Address:
Paris, France
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
AFCP - ATALA
Note:
Pages:
349–354
Language:
URL:
https://www.aclweb.org/anthology/2016.jeptalnrecital-poster.5
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2016.jeptalnrecital-poster.5.pdf