| Autor: |
Liu, Kun, Terzi, Evimaria, Grandison, Tyrone |
| Zdroj: |
Proceedings of the VLDB Endowment; 20240101, Issue: Preprints p1444-1447, 4p |
| Abstrakt: |
We demonstrate ManyAspects -- a document-summarization system that ingests a document and automatically highlights a small set of sentences that are expected to cover the different aspects of the document. The sentences are picked using simple coverage and orthogonality criteria. With ManyAspects, you get a concise yet comprehensive overview of the document without having to spend lots of time drilling down into the details. The system can handle both plain text and syndication feeds (RSS and Atom). It can run either as a stand-alone application or be integrated with Web 2.0 forums to pinpoint different opinions on online discussions for blogs, products, movies, etc. For comparative analysis and exploratory flexibility, the system includes other off-the-shelf text-summarization methods, e.g. k-median clustering and singular value decomposition. Thus, the system allows the user to explore the content of the input document in many different ways. |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
