Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

TREC
2004

favoriteEmaildiscussreport

100views Information Technology» more TREC 2004»

The University of Michigan in Novelty 2004

13 years 5 months ago

The University of Michigan in Novelty 2004

Download trec.nist.gov

This year we participated in the Novelty track. To find the relevant sentences, we combine sentence salience features that are inherited from text summarization domain with other heuristic features based on topic statements. We propose a novel method to extract the new sentences based on the graph-based ranking of the similarity relation between the sentences.

Günes Erkan

Real-time Traffic

Relevant Sentences | Sentence Salience Features | Text Summarization Domain | TREC 2004 | TREC 2008 |

claim paper

Related Content

» Columbia University in the Novelty Track at TREC 2004

» Experiments in Terabyte Searching Genomic Retrieval and Novelty Detection for TREC 2004

» Novelty Question Answering and Genomics The University of Iowa Response

» Using relative novelty to identify useful temporal abstractions in reinforcement learning

» Abstract State Machines An Overview of the Project

» An experimental simulation of multisite software development

» Mining interesting contrast rules for a webbased educational system

» A Virtual Honeypot Framework

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2004
Where	TREC
Authors	Günes Erkan

Comments (0)