• 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.

• Korean Journal of Psychosomatic Medicine
• /
• v.25 no.1
• /
• pp.63-72
• /
• 2017

Objectives : Attention-deficit hyperactivity disorder(ADHD) is characterized by significant impairments in executive functions, with a prevalence of approximately 3-5% of all children worldwide. The goal of this study was to examine the relationship between executive functions and electrophysiological activities in children and adolescents with ADHD. Methods : In 31 patients with ADHD, resting-state EEG was recorded, and Comprehensive Attention Test(CAT), Stroop Color-Word Inference Test(Stroop CWIT), Trail Making Test(TMT), and Wisconsin Card Sorting Test(CST) were administered. Korean version of the ADHD Rating Scale(K-ARS) was assessed. Results : Alpha and beta power positively correlated with the Attention Quotient(AQ), while delta power negatively correlated with AQ from CAT. In the Stroop CWIT, decreased delta power and increased beta power were related to higher performance. Power of the alpha band increased with higher TMT performance. Moreover, delta power negatively correlated with good performance on the CST, while alpha and high gamma band showed a positive correlation. Correlation with the parent-rating of ADHD symptoms showed a negative correlation between alpha power and higher scores on the K-ARS. Conclusions : These findings indicate that relative power in higher frequency bands of EEG is related to the higher executive function in children and adolescents with ADHD, while the association with the relative power in lower frequency bands of EEG seem to be vice versa. Furthermore, the findings suggest that QEEG may be a useful adjunctive tool in assessing patients with ADHD.

• The Journal of the Korea Contents Association
• /
• v.16 no.3
• /
• pp.269-287
• /
• 2016

This study explores of press report on the death of Beongen Yoo based on network analysis and how issue diffuses via Internet and SNS in mainstream news and conservative channels of comprehensive programming. Issue salience, word's visibility and word's connectivity are the main keyword and analysis criteria of this study. Conservative channel of comprehensive programming focused on the surrounding information rather than core information compared to Mainstream media, Conservative channels of comprehensive media was interested in Yu, Beongeon, an article left, brand, rumor of a body and Mainstream media focused on the results of DNA test. Mainstream media covers this case as the discovery of the Yu, Beongeon body, Mainstream media reported as 'the discovery of the body frame, conservative channels of comprehensive programming reports as blame of investigation at the first stage. The former focuses on the cause of death and the latter focuses on the raising of strong doubts frame at the second stage. In case of the third stage the latter covered on the emphasis of the surrounding information. They frames the issue differently based on network analysis. The view point of conservative channel of comprehensive programming is diffused via SNS. This study highlights the role of journalist of mainstream media in the process of agenda-setting

• Journal of Music and Human Behavior
• /
• v.8 no.2
• /
• pp.65-75
• /
• 2011

The purpose of this study was to investigate the effect of vocal and instrumental background music on a verbal memorizing task. Participants were 30 undergraduate and graduate students and were randomly divided into two groups. All participants in both groups took a pretest and a posttest to examine the improvement of the memorization. Background music was inserted during the memorization task. Subjects in Group A listened to a vocal recording whereas Group B listened to the same music except with a cello playing the melody of the vocal part. All participants were asked to take the posttest to examine the improvement of their knowledge after the memorization. The t-test was used to compare the two groups. Results indicated that Group A(8.93) exhibited higher mean scores than Group B(7.46) but there were no significant differences t(28) = 1.38, p < .05. This study implies that lyrics does not distract word memorization and background music does not influence cognition directly.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.459-466
• /
• 2009

While Korean allows the same consonants at the coda of the preceding syllable and at the onset of the following syllable, English does not allow the geminate consonants in the same intervocalic position. Due to this difference between Korean and English, Korean learners of English tend to incorrectly produce geminate consonants for English geminate graphemes as in $su\underline{mm}er$. Based on this observation, a pilot study was designed to investigate how Korean learners of English perceive and produce English doubleton graphemes and singleton graphemes. Twenty Korean college students were asked to perform a forced-choice perception test as well as a production test for the 36 real word stimuli which consist of (near) minimal pairs of singleton and doubleton graphemes. The result showed that the accuracy rates for the words with singleton graphemes were higher than those for the words with doubleton graphemes both in perception and production because the subjects misperceived and misproduced the doubleton graphemes as geminates due to orthographic influence. In addition, the low error rates of the word with voiced stops were accounted for by Korean language transfer. Further, spectrographic analyses were provided where more production errors were witnessed in doubleton grapheme words than singleton grapheme words. Finally, pedagogical implications are provided.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.1-9
• /
• 2010

Authoring tools for sketching the motion of characters to be animated have been studied. However the natural interface for sound editing has not been sufficiently studied. In this paper, I present a novel method that sound sample is selected by speaking sound-imitation words(onomatopoeia). Experiment with the method based on statistical models, which is generally used for pattern recognition, showed up to 97% in the accuracy of recognition. In addition, to address the difficulty of data collection for newly enrolled sound samples, the GLR Test based on only one sample of each sound-imitation word showed almost the same accuracy as the previous method.

• The korean journal of orthodontics
• /
• v.21 no.2 s.34
• /
• pp.287-307
• /
• 1991

This study aimed at examining speech defects of openbite patients, which were analized in terms of formant frequency for vowels and word pronunciation length for consonants. In addition, the upper and lower lip (perioral m.) activity was tested by the EMG. The tongue force was measured by the strain gauge, and the speech discrimination test was carried out. One experimental group and one control group were used for this study and they were respectively composed of six female openbite patients and six normal-occlusion females. Eight monophthongs, two fricatives and two affricatives were chosen for speech analysis. Speeches of the above-mentioned groups were recorded and then analized by the ILS/PC-1 software. Four hundred most frequently used monosyllables were also chosen for discrimination score. Openbite patients showed the following characteristics: 1. Abnormality in case of /a/, $/\varepsilon/$, /e/, /i/ $F_2$ and /e/, /a/ $F_1$. 2. Significantly elongated length in their pronunciation of /h/ and $/C^h/$ and somewhat elongated length also in their pronunciation of /s/ and /c/. 3. Significant upper lip activity according to the EMG test during pronunciation of the bilabial consonants. 4. Relatively weak tongue force according to the strain gauge measurement. 5. According to the speech discrimination test, high rate of misarticulation in case of (a) initial /p/ /s'/ and /ts'/, (b) /a/,$/\varepsilon/$,/e/,/je/,/o/, $/\phi/$,/jo/,/u/,/we/, and /i/ (c) final (equation omitted).

• The Journal of the Korea Contents Association
• /
• v.10 no.7
• /
• pp.133-141
• /
• 2010

The purpose of this paper is to suggest one of effective online questionnaire methods by using web based games. The research examines the interrelation between space design element and emotion language in the background actually used in the web games, and suggests new questionnaire methods to overcome the problems of the insincere answers which is the limitation of online questionnaire methods. The paper is to examine the related references, and compare the merits and demerits between printed and online text based questionnaires. Then it suggests the on-line questionnaire methods based web games which can improve errors of the demerits. The emotional words and phrases database is embodied by the interrelation between the emotional words and four spaces such as a dwelling, a tradition, a commerce and a fantasy based on the position decision value of Gaussian distribution. The paper suggests to be utilized for a population calculability system such as a consumers preference test.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.427-434
• /
• 2014

In this research, it is empirically tested whether firm value after the adoption of IFRS is increased in Korea and China using Tobin's Q model. In Korea, IFRS was mandatorily adopted in 2011 for all companies. China mandated IFRS conversion for public traded companies starting 2007. The revisions bring Chinese standards closer to the IFRS benchmark of internationally recognized quality, but the new standards will not be word-for-word translations of IFRS, though they founded on similar principle. We expect the different adoption process between Korea and China can make different impact of IFRS on firm value. The results are summarized as follows. First, Tobin's Q seems to be increased after the adoption of IFRS, and the firm value is significantly different between before and after IFRS adoption in Korea. Second, Tobin's Q seems to be increased after the adoption of IFRS, but the analysis by t-test is not significantly higher for post IFRS. These results could be a good finding in that the impact of IFRS adoption on firm value is different by adoption process.

• Journal of The Korean Association of Information Education
• /
• v.21 no.2
• /
• pp.161-169
• /
• 2017

We often use spellcheckers in order to correct the syntactic errors in our documents. However, these computer programs are not enough for elementary school students, because their sentences are not smooth even after correcting the syntactic errors in many cases. In this paper, we introduce an automated method for evaluating the smoothness of two synonymous sentences. This method uses a recurrent neural network to solve the problem of long-term dependencies and exploits subwords to cope with the rare word problem. We trained the recurrent neural network language model based on a monolingual corpus of about two million English sentences. In our experiments, the trained model successfully selected the more smooth sentences for all of nine types of test set. We expect that our approach will help in elementary school writing after being implemented as an application for smart devices.