Annotating photos is such a time-consuming, tedious and error-prone data entry task that it discourages most owners of personal photo libraries. B y allowing users to drag labels such as personal names from a scrolling list and drop them on a photo, we believe we can make the task faster, easier and more appealing. Since the names are entered in a database, searching for al l photos of a fiiend...

This paper presents a set of algorithms for distinguishing personal names with multiple real referents in text, based on little or no supervision. The approach utilizes an unsupervised clustering technique over a rich feature space of biographic facts, which are automatically extracted via a language-independent bootstrapping process. The induced clustering of named entities are then partitione...

Semantic dementia patients seem to have better knowledge of information linked to the self. More specifically, despite having severe semantic impairment, these patients show that they have more general information about the people they know personally by direct experience than they do about other individuals they know indirectly. However, the role of direct personal experience remains debated b...

Word Identification has been an important and active issue in Chinese Natural Language Processing. In this paper, a new mechanism, based on the concept of sublanguage, is proposed for identifying unknown words, especially personal names, in Chinese newspapers. The proposed mechanism includes title.driven name recognition, adaptive dynamic word formation, identification of Z-character and 3-char...

Instant messaging (IM) is increasingly popular among not only Internet but also smartphone users. In this paper, we analyze the security issue of an IM application, KakaoTalk, which is the most widely used in South Korea, with a focus on automated friends registration based on contacts sync. We demonstrate that there are multiple ways of collecting victims’ personal information such as their na...

Personal names tend to have many variations differing from country to country. Though there exists a large amount of personal names on the Web, nationality prediction solely based on names has not been fully studied due to its difficulties in extracting subtle character level features. We propose a recurrent neural network based model which predicts nationalities of each name using automatic fe...