Most of modern systems for information retrieval, fusion and management have to deal more and more with information expressed quatitatively (by linguistic labels) since human repo...
Xinde Li, Xianzhong Dai, Jean Dezert, Florentin Sm...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to ...
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
Previous research into the efficiency of text retrieval systems has dealt primarily with methods that consider inverted lists in sequence; these methods are known as term-at-a-tim...
This paper describes a method of detecting Japanese Katakana variants from a large corpus. Katakana words, which are mainly used as loanwords, cause problems with information retr...