Sciweavers

144 search results - page 23 / 29
» Improved Source-Channel Models for Chinese Word Segmentation
Sort
View
ICASSP
2008
IEEE
14 years 2 months ago
An unsupervised web-based topic language model adaptation method
This paper focuses on a solution to better adapt ASR systems, whose language models (LM) are usually trained on topic-independent corpora, to new topics, in particular in the case...
Gwénolé Lecorvé, Guillaume Gr...
ACL
2007
13 years 9 months ago
Bilingual-LSA Based LM Adaptation for Spoken Language Translation
We propose a novel approach to crosslingual language model (LM) adaptation based on bilingual Latent Semantic Analysis (bLSA). A bLSA model is introduced which enables latent topi...
Yik-Cheung Tam, Ian R. Lane, Tanja Schultz
JCB
2000
146views more  JCB 2000»
13 years 7 months ago
Bayesian Segmentation of Protein Secondary Structure
We present a novel method for predicting the secondary structure of a protein from its amino acid sequence. Most existing methods predict each position in turn based on a local wi...
Scott C. Schmidler, Jun S. Liu, Douglas L. Brutlag
ICASSP
2010
IEEE
13 years 8 months ago
Discriminative template extraction for direct modeling
This paper addresses the problem of developing appropriate features for use in direct modeling approaches to speech recognition, such as those based on Maximum Entropy models or S...
Shankar Shivappa, Patrick Nguyen, Geoffrey Zweig
IJCAI
2007
13 years 9 months ago
Simple Training of Dependency Parsers via Structured Boosting
Recently, significant progress has been made on learning structured predictors via coordinated training algorithms such as conditional random fields and maximum margin Markov ne...
Qin Iris Wang, Dekang Lin, Dale Schuurmans