Sciweavers

144 search results - page 16 / 29
» Improved Source-Channel Models for Chinese Word Segmentation
Sort
View
EMNLP
2006
13 years 9 months ago
A Hybrid Markov/Semi-Markov Conditional Random Field for Sequence Segmentation
Markov order-1 conditional random fields (CRFs) and semi-Markov CRFs are two popular models for sequence segmentation and labeling. Both models have advantages in terms of the typ...
Galen Andrew
ICASSP
2011
IEEE
12 years 11 months ago
Improved models for Mandarin speech-to-text transcription
This paper describes recent advances at LIMSI in Mandarin Chinese speech-to-text transcription. A number of novel approaches were introduced in the different system components. Th...
Lori Lamel, Jean-Luc Gauvain, Viet-Bac Le, Ilya Op...
ICMLC
2010
Springer
13 years 5 months ago
An improvement of translation quality with adding key-words in parallel corpus
: In this paper, we propose a new approach to improve the translation quality by adding the Key-Words of a sentence to the parallel corpus. The main idea of the approach is to find...
Liang Tian, Fai Wong, Sam Chao
ICANN
2009
Springer
14 years 2 months ago
Selective Attention Improves Learning
Abstract. We demonstrate that selective attention can improve learning. Considerably fewer samples are needed to learn a source separation problem when the inputs are pre-segmented...
Antti Yli-Krekola, Jaakko Särelä, Harri ...
SKG
2005
IEEE
14 years 1 months ago
DLOnto: A Semantic Information Model for Digital Libraries
In this paper, we propose the Semantic Information Model for Digital Libraries - DLOnto based on the theory of the Semantic Web, and give the formalized definition of and relative ...
Ming Zhang, Zhi-Hong Deng, Shukai Ding, Dongqing Y...