This paper address the problem of entity linking. Specifically, given an entity mentioned in unstructured texts, the task is to link this entity with an entry stored in the existi...
While several hierarchical classification methods have been applied to web content, such techniques invariably rely on a pre-defined taxonomy of documents. We propose a new techni...
When we want information on current events, we often view news programs on TV or news streams on Web sites. A news video stream consists of several scenes, and viewers often gain ...
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...
Since we can hardly get semantics from the low-level features of the image, it is much more difficult to analyze the image than textual information on the Web. Traditionally, textu...