Sciweavers

265 search results - page 10 / 53
» Statistical-Based Approach to Word Segmentation
Sort
View
ICDAR
2009
IEEE
13 years 5 months ago
Italic or Roman: Word Style Recognition without A Priori Knowledge for Old Printed Documents
This paper presents an Italic/Roman word type recognition system without a priori knowledge on the characters' font. This method aims at analyzing old documents in which char...
Loris Eynard, Hubert Emptoz
COLING
2002
13 years 7 months ago
Applying an NVEF Word-Pair Identifier to the Chinese Syllable-to-Word Conversion Problem
Syllable-to-word (STW) conversion is important in Chinese phonetic input methods and speech recognition. There are two major problems in the STW conversion: (1) resolving the ambi...
Jia-Lin Tsai, Wen-Lian Hsu
DIAL
2004
IEEE
149views Image Analysis» more  DIAL 2004»
13 years 11 months ago
Holistic Word Recognition for Handwritten Historical Documents
Most offline handwriting recognition approaches proceed by segmenting words into smaller pieces (usually characters) which are recognized separately. The recognition result of a w...
Victor Lavrenko, Toni M. Rath, R. Manmatha
ACL
2012
11 years 10 months ago
Enhancing Statistical Machine Translation with Character Alignment
The dominant practice of statistical machine translation (SMT) uses the same Chinese word segmentation specification in both alignment and translation rule induction steps in buil...
Ning Xi, Guangchao Tang, Xinyu Dai, Shujian Huang,...
EMNLP
2004
13 years 9 months ago
A New Approach for English-Chinese Named Entity Alignment
Traditional word alignment approaches cannot come up with satisfactory results for Named Entities. In this paper, we propose a novel approach using a maximum entropy model for nam...
Donghui Feng, Yajuan Lü, Ming Zhou