This work presents a new approach to unsupervised abstractive summarization\nbased on maximizing a combination of coverage and fluency for a given length\nconstraint. It introduces a novel method that encourages the inclusion of key\nterms from the original document into the summary: key terms are masked out of\nthe original document and must be filled in by a coverage model using the\ncurrent generated summary. A novel unsupervised training procedure leverages\nthis coverage model along with a fluency model to generate and score summaries.\nWhen tested on popular news summarization datasets, the method outperforms\nprevious unsupervised methods by more than 2 R-1 points, and approaches results\nof competitive supervised methods. Our model attains higher levels of\nabstraction with copied passages roughly two times shorter than prior work, and\nlearns to compress and merge sentences without supervision.\n
Siyu Zhao, Corey Giles, Kevin Huynh, Johannes Kettunen, Paul M Ridker, Mika Kähönen, Jorma Viikari, Terho Lehtimäki, Olli T. Raitakari, Peter J. Meikle, Ville-Petteri Mäkinen, Mika Ala‐Korpela
Discussion(0)
No comments yet. Be the first to comment.