Sciweavers

34 search results - page 2 / 7
» Automatically Creating a Large Number of New Bilingual Dicti...
Sort
View
LKR
2008
13 years 7 months ago
What Types of Translations Hide in Wikipedia?
Abstract. We extend an automatically generated bilingual JapaneseSwedish dictionary with new translations, automatically discovered from the multi-lingual online encyclopedia Wikip...
Jonas Sjöbergh, Olof Sjöbergh, Kenji Ara...
ICDAR
2003
IEEE
13 years 11 months ago
Gabor Filter Based Multi-class Classifier for Scanned Document Images
When scanning documents with a large number of pages such as books, it is often feasible to provide a minimal number of training samples to personalize the system to compensate fo...
Huanfeng Ma, David S. Doermann
ACL
2006
13 years 7 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
ICASSP
2008
IEEE
14 years 6 days ago
Modified polyphone decision tree specialization for porting multilingual Grapheme based ASR systems to new languages
Automatic speech recognition (ASR) systems have been developed only for a very limited number of the estimated 7,000 languages in the world. In order to avoid the evolvement of a ...
Sebastian Stüker
CIKM
2008
Springer
13 years 7 months ago
Large-scale, parallel automatic patent annotation
When researching new product ideas or filing new patents, inventors need to retrieve all relevant pre-existing know-how and/or to exploit and enforce patents in their technologica...
Milan Agatonovic, Niraj Aswani, Kalina Bontcheva, ...