Sciweavers

20833 search results - page 189 / 4167
» Hidden process models
Sort
View
GECCO
2003
Springer
100views Optimization» more  GECCO 2003»
15 years 11 months ago
Studying the Advantages of a Messy Evolutionary Algorithm for Natural Language Tagging
The process of labeling each word in a sentence with one of its lexical categories (noun, verb, etc) is called tagging and is a key step in parsing and many other language processi...
Lourdes Araujo
NLPRS
2001
Springer
15 years 11 months ago
A Hierarchical EM Approach to Word Segmentation
We propose a simple two-level hierarchical probability model for unsupervised word segmentation. By treating words as strings composed of morphemes/phonemes which are themselves c...
Fuchun Peng, Dale Schuurmans
NLPRS
2001
Springer
15 years 11 months ago
Korean to English TV Caption Translator: ""CaptionEye/KE""
In this paper, we present CaptionEye/KE, a Korean to English machine translation system that is applied to a practical TV caption translation. And its experimental evaluation is p...
Seong-il Yang, Young Kil Kim, Young Ae Seo, Sung-K...
PCM
2001
Springer
150views Multimedia» more  PCM 2001»
15 years 11 months ago
Unsupervised Analysis of Human Gestures
Recognition of human gestures is important for analysis and indexing of video. To recognize human gestures on video, generally a large number of training examples for each individu...
Tianshu Wang, Heung-Yeung Shum, Ying-Qing Xu, Nann...
COLT
1994
Springer
15 years 10 months ago
Learning Probabilistic Automata with Variable Memory Length
We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
Dana Ron, Yoram Singer, Naftali Tishby