• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.8
• /
• pp.5565-5570
• /
• 2015

Implicit citation sentence recognition is to locate citation sentences which lacks explicit citation markers, from articles' full-text. State-of-the-art approaches exploit word ngrams, clue words, researcher's surnames, mentions of previous methods, and distance relative to nearest explicit citation sentences, etc., reaching over 50% performance. However, most previous works have been conducted on English. As for Korean, a rule-based method using positive/negative clue patterns was reported to attain the performance of 42%, requiring further improvement. This study attempted to learn to recognize implicit citation sentences from Korean literatures' full-text using Korean lexical features. Different lexical feature units such as Eojeol, morpheme, and Eumjeol were evaluated to determine proper lexical features for Korean implicit citation sentence recognition. In addition, lexical features were combined with the position features representing backward/forward proximities to explicit citation sentences, improving the performance up to over 50%.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.6
• /
• pp.656-661
• /
• 2015

The goal of this paper is to analyze the performance of a word autocomplete system for mobile devices such as smartphones, tablets, and PCs. The proposed system automatically completes a partially typed string into a full word, reducing the time and effort required by a user to enter text on these devices. We collect a large amount of data from Twitter and develop both unigram and bigram dictionaries based on the frequency of words. Using these dictionaries, we analyze the performance of the word autocomplete system and devise a keystroke profit rate and recovery rate as new evaluation metrics that better describe the characteristics of the word autocomplete problem compared to previous measures such as the mean reciprocal rank or recall.