Sciweavers

342 search results - page 43 / 69
» Refining Generative Language Models using Discriminative Lea...
Sort
View
IJCNLP
2005
Springer
14 years 27 days ago
A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation
This paper proposes a chunking strategy to detect unknown words in Chinese word segmentation. First, a raw sentence is pre-segmented into a sequence of word atoms 1 using a maximum...
Guodong Zhou
IANDC
2008
114views more  IANDC 2008»
13 years 7 months ago
Generalizing the Paige-Tarjan algorithm by abstract interpretation
act Interpretation Francesco Ranzato and Francesco Tapparo Dipartimento di Matematica Pura ed Applicata, Universit`a di Padova, Italy The Paige and Tarjan algorithm (PT) for comp...
Francesco Ranzato, Francesco Tapparo
FLAIRS
2008
13 years 9 months ago
Learning a Probabilistic Model of Event Sequences from Internet Weblog Stories
One of the central problems in building broad-coverage story understanding systems is generating expectations about event sequences, i.e. predicting what happens next given some a...
Mehdi Manshadi, Reid Swanson, Andrew S. Gordon
JMLR
2012
11 years 9 months ago
Maximum Margin Temporal Clustering
Temporal Clustering (TC) refers to the factorization of multiple time series into a set of non-overlapping segments that belong to k temporal clusters. Existing methods based on e...
Minh Hoai Nguyen, Fernando De la Torre
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
15 years 2 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...