FREE Registration is required
Overview:
This paper combines the speed and scalability of information retrieval with the generally superior classification accuracy offered by machine learning, yielding a two-phase text classifier that can scale to very large document corpora. They investigate the effect of different methods of formulating the query from the training set, as well as varying the query size. In empirical tests on the Reuters RCV1 corpus of 806,000 documents, they find runtime was easily reduced by a factor of 27x, with a somewhat surprising gain in F-measure compared with traditional text classification.
(Is this item miscategorized? Does it need more tags? Let us know.)
| Format: | Size: | 271 KB | |
| Date: | Jun 2008 | ||
| Pages: | 9 |
People who downloaded this item also downloaded
White Papers, Webcasts, and Resources
- Dynamic Infrastructure Helping Build a Smarter PlanetDelivering Superior Business and IT Services with Agility and Speed IBMRead about a revolutionary strategy for creating a dynamic IT infrastructure that can deliver superior business and IT services with agility and speed.
- Windows Phones and Unified Communications MicrosoftGain a more solid understanding of UC, why its essential for your business today, and what makes Windows phones ideal for secure UC environments.
- Looking for a fast payback? 10 Minutes with Free Tool Can Save Thousands IBMLooking for a fast payback? Spend just 10 minutes with this free online ROI tool and see how a simple technology refresh can save you...
Premier Vendor Content Whitepapers, webcasts & resources from our Power Center Sponsors
Featured Training Courses
- Implementing and Administering Windows 7 in the Enterprise
- CCNA Boot Camp v2.0
- VMware vSphere: Install, Configure, Manage [V4]
- Certified Ethical Hacker
- Management and Leadership Skills
- Browse all Training Courses
-
-
Smart Tech
Expert advice on innovations in healthcare and the green technologies that make it happen.
Find out more
-
Smart Business
Discussion and advice on management issues that revolve around making your world smarter and more useful.
More Smart Advice
-
Smart People
The best and worst moves in the management and strategy trenches.
Learn More




