• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2021

Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.2
• /
• pp.99-107
• /
• 2018

This study started from the public interest purpose to help accessibility for the information acquisition of the vulnerable groups due to visual difficulties such as the elderly and the visually impaired. In this study, the server resources are minimized and implemented in most of the user smart phones. In addition, we implement a method to gather necessary information by collecting only pattern information by utilizing crawl & clipping without having to visit the site of the information of the various sites having the data necessary for the user, and to have it in the server. Especially, we applied the TTS(Text-To-Speech) service composed of smart phone apps and tried to develop a unified customized information collection service based on voice-based information collection method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.386-391
• /
• 2015

This paper proposed the optimal attributes for text classification based on Korean and Chinese linguistic features. The experiments committed to discover which is the best feature among n-grams which is known as language independent, morphemes that have language dependency and some other feature sets consisted with n-grams and morphemes showed best results. This paper used SVM classifier and Internet news for text classification. As a result, bi-gram was the best feature in Korean text categorization with the highest F1-Measure of 87.07%, and for Chinese document classification, 'uni-gram+noun+verb+adjective+idiom', which is the combined feature set, showed the best performance with the highest F1-Measure of 82.79%.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.259-267
• /
• 2003

Though naive Bayes text classifiers are widely used because of its simplicity, the techniques for improving performances of these classifiers have been rarely studied. In this paper, we propose and evaluate some general and effective techniques for improving performance of the naive Bayes text classifier. We suggest document model based parameter estimation and document length normalization to alleviate the Problems in the traditional multinomial approach for text classification. In addition, Mutual-Information-weighted naive Bayes text classifier is proposed to increase the effect of highly informative words. Our techniques are evaluated on the Reuters21578 and 20 Newsgroups collections, and significant improvements are obtained over the existing multinomial naive Bayes approach.

• IE interfaces
• /
• v.22 no.4
• /
• pp.329-335
• /
• 2009

Recently, the use of soft-keyboard is widespread and increases, because various handheld devices were developed such as PDA, navigation, mobile phones with enhanced competence of touchscreen. The use of soft-keyboard requires different characteristics compared to traditional hard-keyboard like QWERTY keyboard: no standard character layout, one finger entry, and cognitive processing time. In this study, therefore, the optimal soft-keyboard layout for one finger text entry in touchscreen environment was investigated among 6 keyboard layouts which were developed based on traditional characteristic of Korean text and the usage frequency of both vowels and consonants. As a result, the interface with Korean text invention order like 'ㄱㄴㄷㄹ' or 'ㅏㅑㅓㅕㅕ' was found to be better than the interface with usage frequency-based arrangement. Especially the vowels were most efficient when separated into two parts; located at the right-hand side and at right below the consonants. In conclusion, the keyboard layout with regard to the Korean text characteristic and the invention order was a more effective layout resulted from the minimum cognitive processing time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.2C
• /
• pp.178-183
• /
• 2008

The videotext brings important semantic clues into video content analysis. In this paper, we propose an automatic binarization method of text region using a stroke filter. Proposed text binarization method consists of stroke filtering, text color polarity determination, and local region growing. By using the responses of dark and bright stroke filters, we can determine color polarity of text region automatically. And the method is robust against complex background, because it considers stroke information of videotexts by using a stroke filter. The effectiveness of our method is verified by experiments on a challenging database.

• Journal of KIISE:Software and Applications
• /
• v.34 no.11
• /
• pp.984-990
• /
• 2007

As the amount of electronic documents increases explosively, automatic text categorization methods are needed to identify those of interest. Most methods use machine learning techniques based on a word set. This paper introduces a new method, called FPTC (FP-Tree based Text Classifier). FP-Tree is a data structure used in data-mining. In this paper, a method of storing text sentence patterns in the FP-Tree structure and classifying text using the patterns is presented. In the experiments conducted, we use our algorithm with a #Mutual Information and Entropy# approach to improve performance. We also present an analysis of the algorithm via an ordinary differential categorization method.

• The Journal of Information Systems
• /
• v.29 no.4
• /
• pp.171-191
• /
• 2020

Purpose The study aims to compare the online review writing behavior of users in China and the United States through text mining on online reviews' text content. In particular, existing studies have verified that there are differences in online reviews between different cultures. Therefore, the purpose of this study is to compare the differences between reviews written by Chinese and American tourists by analyzing text contents of online reviews based on cultural theory. Design/methodology/approach This study collected and analyzed online review data for hotels, targeting Chinese and US tourists who visited Korea. Then, we analyzed review data through text mining like sentiment analysis and topic modeling analysis method based on previous research analysis. Findings The results showed that Chinese tourists gave higher ratings and relatively less negative ratings than American tourists. And American tourists have more negative sentiments and emotions in writing online reviews than Chinese tourists. Also, through the analysis results using topic modeling, it was confirmed that Chinese tourists mentioned more topics about the hotel location, room, and price, while American tourists mentioned more topics about hotel service. American tourists also mention more topics about hotels than Chinese tourists, indicating that American tourists tend to provide more information through online reviews.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1135-1143
• /
• 2021

Recently, text collection using a web crawler for big data analysis has been frequently performed. However, in order to collect only the necessary text from a web page that is complexly composed of numerous tags and texts, there is a cumbersome requirement to specify HTML tags and style attributes that contain the text required for big data analysis in the web crawler. In this paper, we proposed a method of extracting text using the frequency of text appearing in web pages without specifying HTML tags and style attributes. In the proposed method, the text was extracted from the DOM tree of all collected web pages, the frequency of appearance of the text was analyzed, and the main text was extracted by excluding the text with high frequency of appearance. Through this study, the superiority of the proposed method was verified.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.