Osamu Imaichi

Learn More
$EVWUDFW 7KLV SDSHU GHVFULEHV D WHUP H[WUDFWLRQ PHWKRG WKDW XVHV D QRYHO PHDVXUH WR GHWHUPLQH WKH UHSUHVHQWDWLYHQHVV L H LQIRUPDWLYHQHVV RU GRPDLQ VSHFLILFLW\ RI D WHUP 7KLV PHDVXUH LV GHILQHG E\ QRUPDOL]LQJ WKH GLVWDQFH EHWZHHQ WKH ZRUG GLVWULEXWLRQ RI WKH GRFXPHQWV FRQWDLQLQJ WKH TXHU\ WHUP DQG WKH ZRUG GLVWULEXWLRQ RI WKH ZKROH FRUSXV 7KH PHDVXUH FDQ(More)
This paper describes an integrated method for processing grammatically i l l formed inputs We use partial parses of the input for recov ering from parsing failure In order to select partial parses appropriate for error recovery, cost and reward are assigned to them Cost and reward represent the badness and goodness of a partial parse, respectively The most(More)
This year’s MedNLP[1] has two tasks: de-identification and complaint and diagnosis. We tested both machine learning based methods and an ad-hoc rule-based method for the two tasks. For the de-identification task, the rule-based method got slightly higher results, while for the complaint and diagnosis task, the machine learning based method had much higher(More)
A novel thesaurus named a “word-sense association network” is proposed for the first time. It consists of nodes representing word senses, each of which is defined as a set consisting of a word and its translation equivalents, and edges connecting topically associated word senses. This word-sense association network is produced from a bilingual dictionary(More)