• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.438-440
• /
• 2014

Recently it is used commercially to actively move the data from the SNS service. Therefore, we propose a method that can accurately analyze the information related to the reputation of companies and products in real time SNS environment in this paper.Identify the relationship between words by performing morphological analysis on the text data gathered by crawling the SNS scheme. In addition, it shows the visualization to analyze statistically through a established emotional dictionary morphemes are extracted from the sentence. Here, if the extracted word is not exist in sentimental dictionary. Also, we propose the algorithm that add the word to emotional dictionary automatically.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4648-4663
• /
• 2020

This paper proposes the Lempel-Ziv 4(LZ4) compression accelerator optimized for scale-out servers in data centers. In order to reduce CPU loads caused by compression, we propose an accelerator solution and implement the accelerator on an Field Programmable Gate Array(FPGA) as heterogeneous computing. The LZ4 compression hardware accelerator is a fully pipelined architecture and applies 16 dictionaries to enhance the parallelism for high throughput compressor. Our hardware accelerator is based on the 20-stage pipeline and dictionary architecture, highly customized to LZ4 compression algorithm and parallel hardware implementation. Proposing dictionary architecture allows achieving high throughput by comparing input sequences in multiple dictionaries simultaneously compared to a single dictionary. The experimental results provide the high throughput with intensively optimized in the FPGA. Additionally, we compare our implementation to CPU implementation results of LZ4 to provide insights on FPGA-based data centers. The proposed accelerator achieves the compression throughput of 639MB/s with fine parallelism to be deployed into scale-out servers. This approach enables the low power Intel Atom processor to realize the Hadoop storage along with the compression accelerator.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.19-26
• /
• 2020

In this paper, we propose a method to analyze the loss region of the dictionary-based super resolution result learned for image quality improvement and to map the learning data according to the analyzed loss region. In the conventional learned dictionary-based method, a result different from the feature configuration of the input image may be generated according to the learning image, and an unintended artifact may occur. The proposed method estimate loss information of low resolution images by analyzing the reconstructed contents to reduce inconsistent feature composition and unintended artifacts in the example-based super resolution process. By mapping the training data according to the final interpolation feature map, which improves the noise and pixel imbalance of the estimated loss information using a Gaussian-based kernel, it generates super resolution with improved noise, artifacts, and staircase compared to the existing super resolution. For the evaluation, the results of the existing super resolution generation algorithms and the proposed method are compared with the high-definition image, which is 4% better in the PSNR (Peak Signal to Noise Ratio) and 3% in the SSIM (Structural SIMilarity Index).

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.391-396
• /
• 2024

This study proposes a novel reverse N-Gram approach to overcome the limitations of traditional N-Gram methods and enhance performance in building an entity dictionary specialized for the healthcare sector. The proposed reverse N-Gram technique allows for more precise analysis and processing of the complex linguistic features of healthcare-related big data. To verify the efficiency of the proposed method, big data on healthcare and digital health announced during the Consumer Electronics Show (CES) held each January was collected. Using the Python programming language, 2,185 news titles and summaries mentioned from January 1 to 31 in 2010 and from January 1 to 31 in 2024 were preprocessed with the new reverse N-Gram method. This resulted in the stable construction of a dictionary for natural language processing in the healthcare field.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1073-1089
• /
• 2006

The goal of Natural Language Processing(NLP) is to make a computer understand a natural language and to deliver the meanings of natural language to humans. Word sense Disambiguation(WSD is a very important technology to achieve the goal of NLP. In this paper, we describe a technology for automatic homonyms disambiguation using both Mutual Information(MI) and a Sense-Tagged Compound Noun Dictionary. Previous research work using word definitions in dictionary suffered from the problem of data sparseness because of the use of exact word matching. Our work overcomes this problem by using MI which is an association measure between words. To reflect language features, the rate of word-pairs with MI values, sense frequency and site of word definitions are used as weights in our system. We constructed a Sense-Tagged Compound Noun Dictionary for high frequency compound nouns and used it to resolve homonym sense disambiguation. Experimental data for testing and evaluating our system is constructed from QA(Question Answering) test data which consisted of about 200 query sentences and answer paragraphs. We performed 4 types of experiments. In case of being used only MI, the result of experiment showed a precision of 65.06%. When we used the weighted values, we achieved a precision of 85.35% and when we used the Sense-Tagged Compound Noun Dictionary, we achieved a precision of 88.82%, respectively.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.393-402
• /
• 2016

To compensate for limited the satisfaction survey currently conducted by Korea Metrological Administration (KMA), a sentiment analysis via a social networking service (SNS) can be utilized. From 2011 to 2014, with the sentiment analysis, Twitter who had commented 'KMA' had collected, then, using $Na{\ddot{i}}ve$ Bayes classification, we were classified into three sentiments: positive, negative, and neutral sentiments. An additional dictionary was made with morphemes appeared only in the positive, negative, and neutral sentiments of basic $Na{\ddot{i}}ve$ Bayes classification, thus the accuracy of sentiment analysis was improved. As a result, when sentiments were classified with a basic $Na{\ddot{i}}ve$ Bayes classification, the training data were reproduced about 75% accuracy rate. Whereas, when classifying with the additional dictionary, it showed 97% accuracy rate. When using the additional dictionary, sentiments of verification data was classified with about 75% accuracy rate. Lower classification accuracy rate would be improved by not only a qualified dictionary that has increased amount of training data, including diverse keywords related to weather, but continuous update of the dictionary. Meanwhile, contrary to the sentiment analysis based on dictionary definition of individual vocabulary, if sentiments are classified into meaning of sentence, increased rate of negative sentiment and change in satisfaction could be explained. Therefore, the sentiment analysis via SNS would be considered as useful tool for complementing surveys in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.5
• /
• pp.39-48
• /
• 2002

long with the rapid spread of the Internet, a new class of commercial applications which process transactions with respect to electronic dictionaries become popular Typical examples are Internet search engines. In this paper, we present a new approach to achieving high performance electronic dictionaries. Different from the conventional approach which use Trie data structures for the implementation of electronic dictionaries, our approach used multi-dimensional binary trees. In this paper, we present the implementation of our electronic dictionary ED-MBT(Electronic Dictionary based on Multidimensional Binary Tree). Exhaustive performance study is also presented to assess the performance impact of ED-MBT on the real world applications.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.448-448
• /
• 2001

The definitions in Korean dictionary not only describe meanings of title, but also include various semantic information such as hypernymy/hyponymy, meronymy/holonymy, polysemy, homonymy, synonymy, antonymy, and semantic features. This paper purposes to implement a parser as the basic tool to acquire automatically the semantic information from the definitions in Korean dictionary. For this purpose, first we constructed the part-of-speech tagged corpus and the tree tagged corpus from the definitions in Korean dictionary. And then we automatically extracted from the corpora the frequency of words which are ambiguous in part-of-speech tag and the grammar rules and their probability based on the statistical method. The parser is a kind of the probabilistic chart parser that uses the extracted data. The frequency of words which are ambiguous in part-of-speech tag and the grammar rules and their probability resolve the noun phrase's structural ambiguity during parsing. The parser uses a grammar factoring, Best-First search, and Viterbi search In order to reduce the number of nodes during parsing and to increase the performance. We experiment with grammar rule's probability, left-to-right parsing, and left-first search. By the experiments, when the parser uses grammar rule's probability and left-first search simultaneously, the result of parsing is most accurate and the recall is 51.74% and the precision is 87.47% on raw corpus.

• Journal of English Language & Literature
• /
• v.55 no.6
• /
• pp.1139-1161
• /
• 2009

This paper deals with the reduction of unstressed prevocalic /u/ and the appearance of /w/ which are observed in such words as ambiguity [ˌæm bǝ ˈgju: ǝ ti] - ambiguous [æm ˈbɪ gjǝ wǝs]. This phenomenon is recorded in Merriam-Webster Online Dictionary, Webster's Third New International Dictionary, Unabridged, and the draft revisions of Oxford English Dictionary Online. Since this phenomenon has not been studied in detail up to now, this paper aims 1) to collect the data related to the reduction of unstressed prevocalic /u/, 2) to classify them systematically, and 3) to explain the phenomenon in terms of Optimality Theory. In the course of analysis, Prevocalic Lengthening, which is crucial to the preservation of unstressed prevocalic /u/, is reinterpreted as one of the ways to prevent hiatus (annual /æ nju: ǝl/). /w/-insertion is another way to prevent hiatus (annual /æ njǝ wǝl/). In addition it is argued that prevocalic /u/ behaves differently from prevocalic /i/ due to the difference in the articulators involved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.