Sciweavers

801 search results - page 68 / 161
» The Inefficiency of Batch Training for Large Training Sets
Sort
View
ALENEX
2001
103views Algorithms» more  ALENEX 2001»
13 years 10 months ago
Travel Planning with Self-Made Maps
Speed-up techniques that exploit given node coordinates have proven useful for shortest-path computations in transportation networks and geographic information systems. To facilita...
Ulrik Brandes, Frank Schulz, Dorothea Wagner, Thom...
ANLP
2000
86views more  ANLP 2000»
13 years 10 months ago
A Finite State and Data-Oriented Method for Grapheme to Phoneme Conversion
A finite-state method, based on leftmost longestmatch replacement, is presented for segmenting words into graphemes, and for converting graphemes into phonemes. A small set of han...
Gosse Bouma
ACL
2010
13 years 7 months ago
Learning Phrase-Based Spelling Error Models from Clickthrough Data
This paper explores the use of clickthrough data for query spelling correction. First, large amounts of query-correction pairs are derived by analyzing users' query reformula...
Xu Sun, Jianfeng Gao, Daniel Micol, Chris Quirk
ICDAR
2005
IEEE
14 years 2 months ago
Handwriting Matching and Its Application to Handwriting Synthesis
Since it is extremely expensive to collect a large volume of handwriting samples, synthesized data are often used to enlarge the training set. We argue that, in order to generate ...
Yefeng Zheng, David S. Doermann
SIGCSE
2009
ACM
213views Education» more  SIGCSE 2009»
14 years 9 months ago
Engaging middle school teachers and students with alice in a diverse set of subjects
This paper describes the integration of the Alice 3D virtual worlds environment into a diverse set of subjects in middle school, including the development of tutorials, example wo...
Susan H. Rodger, Jenna Hayes, Gaetjens Lezin, Henr...