Sciweavers

96 search results - page 17 / 20
» Lightly supervised and unsupervised acoustic model training
Sort
View
ICTAI
2009
IEEE
14 years 2 months ago
EBLearn: Open-Source Energy-Based Learning in C++
Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based ...
Pierre Sermanet, Koray Kavukcuoglu, Yann LeCun
SIGDIAL
2010
13 years 5 months ago
The Effects of Discourse Connectives Prediction on Implicit Discourse Relation Recognition
Implicit discourse relation recognition is difficult due to the absence of explicit discourse connectives between arbitrary spans of text. In this paper, we use language models to...
Zhi Min Zhou, Man Lan, Zhengyu Niu, Yu Xu, Jian Su
NLE
2010
127views more  NLE 2010»
13 years 5 months ago
Class-based approach to disambiguating Levin verbs
Lapata and Brew (2004) (hereafter LB04) obtain from untagged texts a statistical prior model that is able to generate class preferences for ambiguous Levin (1993) verbs (hereafter...
Jianguo Li, Chris Brew
3DOR
2010
13 years 2 months ago
Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes
We introduce a new framework for the automatic selection of the best views of 3D models. The approach is based on the assumption that models belonging to the same class of shapes ...
Hamid Laga
BIBM
2008
IEEE
142views Bioinformatics» more  BIBM 2008»
14 years 1 months ago
Using Global Sequence Similarity to Enhance Biological Sequence Labeling
Identifying functionally important sites from biological sequences, formulated as a biological sequence labeling problem, has broad applications ranging from rational drug design ...
Cornelia Caragea, Jivko Sinapov, Drena Dobbs, Vasa...