Papers
arxiv:2210.15553

Improving abstractive summarization with energy-based re-ranking

Published on Oct 27, 2022
Authors:
,

Abstract

Current abstractive summarization systems present important weaknesses which prevent their deployment in real-world applications, such as the omission of relevant information and the generation of factual inconsistencies (also known as hallucinations). At the same time, automatic evaluation metrics such as CTC scores have been recently proposed that exhibit a higher correlation with human judgments than traditional lexical-overlap metrics such as ROUGE. In this work, we intend to close the loop by leveraging the recent advances in summarization metrics to create quality-aware abstractive summarizers. Namely, we propose an energy-based model that learns to re-rank summaries according to one or a combination of these metrics. We experiment using several metrics to train our energy-based re-ranker and show that it consistently improves the scores achieved by the predicted summaries. Nonetheless, human evaluation results show that the re-ranking approach should be used with care for highly abstractive summaries, as the available metrics are not yet sufficiently reliable for this purpose.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2210.15553 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2210.15553 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2210.15553 in a Space README.md to link it from this page.

Collections including this paper 2