Multi-ERSS and ERSS 2004
Submitted by rene on Thu, 2010-08-26 06:57
Printer-friendly version
PDF version
Printer-friendly versionPDF version| Title | {Multi-ERSS and ERSS 2004} |
| Publication Type | Conference Paper |
| Year of Publication | 2004 |
| Authors | Bergler, S., R. Witte, Z. Li, M. Khalife, Y. Chen, M. Doandes, and A. Andreevskaia |
| Refereed Designation | Non-Refereed |
| Conference Name | Proceedings of Document Understanding Workshop (DUC 2004) |
| Date Published | May 6–7 |
| Publisher | NIST |
| Conference Location | Boston Park Plaza Hotel and Towers, Boston, USA |
| Abstract | Last year, we presented a system, ERSS, which constructed 10 word summaries in form of a list of noun phrases. It was based on a knowledge-poor extraction of noun phrase coreference chains implemented on a fuzzy set theoretic base. This year we present the performance of an improved version, ERSS 2004 and an extension of the same basic system: Multi-ERSS constructs 100-word extract summaries for clusters of texts. With very few modifications we ran ERSS 2004 on Tasks 1 and 3 and Multi-ERSS on Tasks 2, 4, and 5, scoring generally above average in all but the linguistic quality aspects. |
| URL | http://www-nlpir.nist.gov/projects/duc/pubs/2004papers/concordia.witte.pdf |
| Copyright | Copyright © 2004 Sabine Bergler, René Witte, Zhuoyan Li, Michelle Khalifé, Yunyu Chen, Monia Doandes, and Alina Andreevskaia. |
| Attachment | Size |
|---|---|
| concordia.witte_.pdf | 79.8 KB |
»
- Login to post comments
- Tagged
- XML
- BibTex
- Google Scholar
