Source PaperYearLineSentence
N03-1015 2003 35
It is based on the sense-vs.-clue correlation matrix calculation method we originally developed for unsupervised WSD (Kaji and Morimoto, 2002) (self citation)
C04-1105 2004 22
The second one is a newly devised method using the ratio of associated words that sug gest each translation equivalent; it was inspired by a research on word-sense disambiguation using bilin gual comparable corpora (Kaji and Morimoto 2002) (self citation)
C04-1105 2004 50
This can be done by using the sense-vs.-clue correlation algorithm that the author developed for unsupervised word-sense disambiguation (Kaji and Morimoto 2002) (self citation)
W10-3205 2010 12
Compara ble corpora can be used to determine which word associations suggest which translations of the word (Kaji and Morimoto, 2002) (self citation)
P13-2096 2013 36
Hence, unsupervised WSD approaches (Diab and Resnik, 2002; Kaji and Morimoto, 2002; Mihalcea et al, 2004; Jean,2004; Khapra et al, 2011) attract most of the re searchers
P13-2096 2013 9
In multilingual unsupervised scenario, either comparable or parallel corpora have been used by past researchers for disam biguation (Dagan et al, 1991; Diab and Resnik, 2002; Kaji and Morimoto, 2002; Specia et al, 2005; Lefever and Hoste, 2010; Khapra et al, 2011)