Sciweavers

501 search results - page 28 / 101
» Improving Language Models by Clustering Training Sentences
Sort
View
ACL
2006
13 years 9 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
NIPS
2004
13 years 9 months ago
Semi-supervised Learning with Penalized Probabilistic Clustering
While clustering is usually an unsupervised operation, there are circumstances in which we believe (with varying degrees of certainty) that items A and B should be assigned to the...
Zhengdong Lu, Todd K. Leen
FGR
2002
IEEE
171views Biometrics» more  FGR 2002»
14 years 26 days ago
An Approach Based on Phonemes to Large Vocabulary Chinese Sign Language Recognition
Hitherto, the major challenge to sign language recognition is how to develop approaches that scale well with increasing vocabulary size. In this paper we present an approach to la...
Chunli Wang, Shiguang Shan, Wen Gao
NAACL
2010
13 years 5 months ago
From Baby Steps to Leapfrog: How "Less is More" in Unsupervised Dependency Parsing
We present three approaches for unsupervised grammar induction that are sensitive to data complexity and apply them to Klein and Manning's Dependency Model with Valence. The ...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
EMNLP
2008
13 years 9 months ago
Learning to Predict Code-Switching Points
Predicting possible code-switching points can help develop more accurate methods for automatically processing mixed-language text, such as multilingual language models for speech ...
Thamar Solorio, Yang Liu