Sciweavers

154 search results - page 18 / 31
» Discriminative n-gram language modeling
Sort
View
INTERSPEECH
2010
14 years 6 months ago
Investigation of full-sequence training of deep belief networks for speech recognition
Recently, Deep Belief Networks (DBNs) have been proposed for phone recognition and were found to achieve highly competitive performance. In the original DBNs, only framelevel info...
Abdel-rahman Mohamed, Dong Yu, L. Deng
ACL
2012
13 years 2 months ago
Historical Analysis of Legal Opinions with a Sparse Mixed-Effects Latent Variable Model
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
NAACL
2010
14 years 9 months ago
Improved Models of Distortion Cost for Statistical Machine Translation
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
COLING
2010
14 years 6 months ago
Joint Parsing and Translation
Tree-based translation models, which exploit the linguistic syntax of source language, usually separate decoding into two steps: parsing and translation. Although this separation ...
Yang Liu, Qun Liu
LADS
2007
Springer
15 years 5 months ago
Measuring Complexity of Multi-agent Simulations - An Attempt Using Metrics
Abstract The variety of existing agent-based simulations is overwhelming. However – especially when comparing agent-based simulation to other simulation paradigms, a reference fr...
Franziska Klügl