Analyzing Sentence Fusion in Abstractive Summarization

Abstract

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.

Publication
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Workshop on New Frontiers in Summarization.
Date