17049 search results - page 170 / 3410 » cans 2007 |
NAACL
2007
15 years 8 days ago
2007
This paper describes an efficient method to extract large n-best lists from a word graph produced by a statistical machine translation system. The extraction is based on the k sh...
NAACL
2007
15 years 8 days ago
2007
Training statistical models to detect nonnative sentences requires a large corpus of non-native writing samples, which is often not readily available. This paper examines the exte...
NAACL
2007
15 years 8 days ago
2007
Most dialogue systems are built with a single task in mind. This makes the extension of an existing system one of the major problems in the field as large parts of the system hav...
NIPS
2007
15 years 8 days ago
2007
In this paper we model relational random variables on the edges of a network using Gaussian processes (GPs). We describe appropriate GP priors, i.e., covariance functions, for dir...
NIPS
2007
15 years 8 days ago
2007
We demonstrate that log-linear grammars with latent variables can be practically trained using discriminative methods. Central to efficient discriminative training is a hierarchi...