Abstract
We describe Rosetta, an indexing and retrieval system for collections of research papers. Rosetta indexes papers in a collection based on the way they have been described when referenced by other papers in the collection. With this technique, indices for papers describe information provided in the same way a query describes information needed. Using Rosetta, simple natural language queries retrieve high-precision results in which descriptions based on citations clearly summarize retrieved papers; allowing users to quickly determine which papers most closely meet their information needs.
Original language | English (US) |
---|---|
Pages (from-to) | 741-750 |
Number of pages | 10 |
Journal | Proceedings of the ASIS Annual Meeting |
Volume | 36 |
State | Published - Dec 1 1999 |
ASJC Scopus subject areas
- Information Systems
- Library and Information Sciences