Sciweavers

903 search results - page 165 / 181
» Dependence language model for information retrieval
Sort
View
EMNLP
2007
13 years 9 months ago
Improving Query Spelling Correction Using Web Search Results
Traditional research on spelling correction in natural language processing and information retrieval literature mostly relies on pre-defined lexicons to detect spelling errors. Bu...
Qing Chen, Mu Li, Ming Zhou
CDVE
2007
Springer
124views Visualization» more  CDVE 2007»
14 years 1 months ago
"Integrare", a Collaborative Environment for Behavior-Oriented Design
In order to build complex, large-scale, dependable systems it is necessary to use a development environment with an integrated set of capabilities that supports editing and formal...
Lian Wen, Robert Colvin, Kai Lin, John Seagrott, N...
JMLR
2012
11 years 10 months ago
Deep Learning Made Easier by Linear Transformations in Perceptrons
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Tapani Raiko, Harri Valpola, Yann LeCun
TSD
2007
Springer
14 years 1 months ago
Accurate Unlexicalized Parsing for Modern Hebrew
Many state-of-the-art statistical parsers for English can be viewed as Probabilistic Context-Free Grammars (PCFGs) acquired from treebanks consisting of phrase-structure trees enri...
Reut Tsarfaty, Khalil Sima'an
KDD
2003
ACM
146views Data Mining» more  KDD 2003»
14 years 8 months ago
Style mining of electronic messages for multiple authorship discrimination: first results
This paper considers the use of computational stylistics for performing authorship attribution of electronic messages, addressing categorization problems with as many as 20 differ...
Shlomo Argamon, Marin Saric, Sterling Stuart Stein