Objective Function Learning to Match Human Judgements for Optimization-Based Summarization

Maxime Peyrard, Iryna Gurevych


Abstract
Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments. In this work, we learn a summary-level scoring function 𝜃 including human judgments as supervision and automatically generated data as regularization. We extract summaries with a genetic algorithm using 𝜃 as a fitness function. We observe strong and promising performances across datasets in both automatic and manual evaluation.
Anthology ID:
N18-2103
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
654–660
Language:
URL:
https://aclanthology.org/N18-2103
DOI:
10.18653/v1/N18-2103
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/N18-2103.pdf