Sciweavers

221 search results - page 37 / 45
» Data Hiding Techniques Using Prime and Natural Numbers
Sort
View
ACL
2006
13 years 9 months ago
Weakly Supervised Named Entity Transliteration and Discovery from Multilingual Comparable Corpora
Named Entity recognition (NER) is an important part of many natural language processing tasks. Current approaches often employ machine learning techniques and require supervised d...
Alexandre Klementiev, Dan Roth
UAI
2003
13 years 8 months ago
Exploiting Locality in Searching the Web
Published experiments on spidering the Web suggest that, given training data in the form of a (relatively small) subgraph of the Web containing a subset of a selected class of tar...
Joel Young, Thomas Dean
SPEECH
2010
225views more  SPEECH 2010»
13 years 5 months ago
Automatic recognition of regional phonological variation in conversational interaction
One key aspect of face-to-face communication concerns the differences that may exist between speakers’ native regional accents. This paper focuses on the characterization of re...
Vincent Aubanel, Noël Nguyen
CSL
2007
Springer
13 years 7 months ago
Soft indexing of speech content for search in spoken documents
The paper presents the Position Specific Posterior Lattice (PSPL), a novel lossy representation of automatic speech recognition lattices that naturally lends itself to efficient ...
Ciprian Chelba, Jorge Silva, Alex Acero
SIGMOD
2008
ACM
142views Database» more  SIGMOD 2008»
14 years 7 months ago
Cost-based variable-length-gram selection for string collections to support approximate queries efficiently
Approximate queries on a collection of strings are important in many applications such as record linkage, spell checking, and Web search, where inconsistencies and errors exist in...
Xiaochun Yang, Bin Wang, Chen Li