Sciweavers

1931 search results - page 63 / 387
» Why we blog
Sort
View
ICASSP
2011
IEEE
13 years 13 days ago
Why word error rate is not a good metric for speech recognizer training for the speech translation task?
Speech translation (ST) is an enabling technology for cross-lingual oral communication. A ST system consists of two major components: an automatic speech recognizer (ASR) and a ma...
Xiaodong He, Li Deng, Alex Acero
SIGIR
2010
ACM
14 years 18 days ago
Proximity-based opinion retrieval
Blog post opinion retrieval aims at finding blog posts that are relevant and opinionated about a user’s query. In this paper we propose a simple probabilistic model for assigni...
Shima Gerani, Mark James Carman, Fabio Crestani
CIKM
2008
Springer
13 years 10 months ago
Topological analysis of an online social network for older adults
Social network systems on the Internet, such MySpace and LinkedIn, are growing in popularity around the world. The level of such activity is now comparable to that associated with...
Marcella Wilson, Charles K. Nicholas
WWW
2008
ACM
14 years 9 months ago
Why web 2.0 is good for learning and for research: principles and prototypes
The term "Web 2.0" is used to describe applications that distinguish themselves from previous generations of software by a number of principles. Existing work shows that...
Carsten Ullrich, Kerstin Borau, Heng Luo, Xiaohong...
ICFP
2004
ACM
14 years 8 months ago
Types, potency, and idempotency: why nonlinearity and amnesia make a type system work
Useful type inference must be faster than normalization. Otherwise, you could check safety conditions by running the program. We analyze the relationship between bounds on normali...
Harry G. Mairson, Peter Møller Neergaard