70 search results - page 14 / 14 » Using self-supervised word segmentation in Chinese informati... |
LREC
2010
13 years 7 months ago
2010
In Japanese, there are a large number of notational variants of words. This is because Japanese words are written in three kinds of characters: kanji (Chinese) characters, hiragar...
KDD
2006
ACM
14 years 5 months ago
2006
ACM
In many text classification applications, it is appealing to take every document as a string of characters rather than a bag of words. Previous research studies in this area mostl...
KDD
2004
ACM
14 years 5 months ago
2004
ACM
We consider the problem of improving named entity recognition (NER) systems by using external dictionaries--more specifically, the problem of extending state-of-the-art NER system...
MT
2007
13 years 5 months ago
2007
This paper describes the framework of the StatCan Daily Translation Extraction System (SDTES), a computer system that maps and compares webbased translation texts of Statistics Can...
ICDAR
1997
IEEE
13 years 9 months ago
1997
IEEE
ABSTRACT: OCR is an error-prone process. It is time-consuming and expensive to manually proofread OCR results. The errors remaining in OCRed texts can cause serious problems in rea...