Sciweavers

1209 search results - page 170 / 242
» Using Prosodic Features in Language Models for Meetings
Sort
View
ACL
1997
15 years 1 months ago
A Model of Lexical Attraction and Repulsion
This paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-...
Doug Beeferman, Adam L. Berger, John D. Lafferty
ACL
2009
14 years 9 months ago
Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Yoshimasa Tsuruoka, Jun-ichi Tsujii, Sophia Anania...
COLING
2010
14 years 6 months ago
A Working Report on Statistically Modeling Dative Variation in Mandarin Chinese
Dative variation is a widely observed syntactic phenomenon in world languages (e.g. I gave John a book and I gave a book to John). It has been shown that which surface form will b...
Yao Yao, Feng-hsi Liu
EMNLP
2009
14 years 9 months ago
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests
Many statistical translation models can be regarded as weighted logical deduction. Under this paradigm, we use weights from the expectation semiring (Eisner, 2002), to compute fir...
Zhifei Li, Jason Eisner
JMLR
2012
13 years 2 months ago
On Nonparametric Guidance for Learning Autoencoder Representations
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle