What does this research mean for the field?

Unsupervised metrics, likely based on question-answering, can be utilized as effective reward signals for training reinforced text summarization models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 1, 2019Open Access

Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

Key Points

Key points are not available for this paper at this time.

Abstract

Thomas Scialom, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Bookmark

View Full Paper