logo Idiap Research Institute        
 [BibTeX] [Marc21]
Sentence-level Planning for Especially Abstractive Summarization
Type of publication: Conference paper
Citation: Marfurt_NEWSUM_2021
Publication status: Published
Booktitle: Proceedings of the Third Workshop on New Frontiers in Summarization
Year: 2021
Month: November
Pages: 1--14
Publisher: Association for Computational Linguistics
Address: Online and in Dominican Republic
URL: https://aclanthology.org/2021....
Abstract: Abstractive summarization models heavily rely on copy mechanisms, such as the pointer network or attention, to achieve good performance, measured by textual overlap with reference summaries. As a result, the generated summaries stay close to the formulations in the source document. We propose the *sentence planner* model to generate more abstractive summaries. It includes a hierarchical decoder that first generates a representation for the next summary sentence, and then conditions the word generator on this representation. Our generated summaries are more abstractive and at the same time achieve high ROUGE scores when compared to human reference summaries. We verify the effectiveness of our design decisions with extensive evaluations.
Keywords: Natural language processing, Summarization
Projects Intrepid
Authors Marfurt, Andreas
Henderson, James
Added by: [UNK]
Total mark: 0