• 한국음향학회지
• /
• 제10권2호
• /
• pp.29-35
• /
• 1991

본 논문에서는 변이음 단위의 Hidden Markov Model (HMM)을 이용하여 고립단어를 인식하는 방법을 논한다. 변이음 단위로 HMM을 구성하여 변이음 사전을 만들고, 이 변이음 사전을 이용하여 단어 사전을 구성한다. 변이음 HMM을 이용하여 단어를 구성하려면 변이음 간의 천이확률이 계산되어야 하므로 본 연구에서는 변이음 간의 천이 확률의 영향을 측정하여 그 변이음으로 이루어지는 임의의 단어를 적응없이 적은 수의 적응 데이터로 단어모델을 구성 인식하는 것을 설명한다. 비교를 위하여 단어인식 HMM으로 인식 실험을 한 결과, 변이음 단위 HMM이 적은 기억 용량과 적은 데이터의 훈련으로 단어단위 HMM 이상의 인식률을 얻을 수 있음을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

• 한국응급구조학회지
• /
• 제24권1호
• /
• pp.85-92
• /
• 2020

Purpose: The purpose of this study was to analyze the English abstract key words found within the Korea Society of Emergency Medical Services journal using text mining techniques to determine the adherence of these terms with Medical Subject Headings (MeSH) and identify key word trends. Methods: We analyzed 212 papers that were published from 2012 to 2019. R software, web scraping, and frequency analysis of key words were conducted using R's basic and text mining packages. Additionally, the Word Clouds package was used for visualization. Results: The average number of key words used per study was 3.9. Word cloud visualization revealed that CPR was most prominent in the first half and emergency medical technician was most frequently used during the second half. There were a total of 542 (64.9%) words that exactly matched the MeSH listed words. A total of 293 (35%) key words did not match MeSH listed words. Conclusion: Researchers should obey submission rules. Further, journals should update their respective submission rules. MeSH key words that are frequently cited should be suggested for use.

• Asia pacific journal of information systems
• /
• 제25권3호
• /
• pp.563-578
• /
• 2015

Forecasting daily box-office performance is critical for planning the distribution of marketing resources, and by extension, maximizing profits. For certain movies, the number of viewers increases rapidly at the beginning of their theatrical run, and the increments slow down later. Other movies are not popular in the beginning, but the audience sizes grow rapidly afterward. Thus, the audience attendance of movies grow in different trajectories, which are influenced by various factors including marketing budget, distributors, directors, actors, and word of mouth. In this paper, we propose a method for predicting the daily performance trajectory of running movies based on the hierarchical linear model. More specifically, we focus on the effect of online word of mouth on the shape of the growth curves. We fitted the mean trajectory of the cumulative audience size as a cubic function of time, and allowed the intercept and slope to vary movie-to-movie. Moreover, we fitted the linear slope with a function of online word of mouth predictors to help determine the shape of the trajectories. Finally, we provide performance predictions for individual movies.

• 말소리와 음성과학
• /
• 제7권1호
• /
• pp.107-116
• /
• 2015

The present experiment investigated the effect of word length on the length of f0 intervals for North Kyungsang children. In order to find out the lengths of the f0 intervals, the f0 values at the midpoints of vowels in words were measured. F0 estimates were computed as intervals consistent with the logarithmic scale corresponding to the number of syllables in the words. The results indicated that the mean f0 intervals in words of different lengths showed a significant difference for the HH in HH vs. HHL and the LH in LH vs. LLH for North Kyungsang children. Adult speakers from the North Kyungsang region significantly differed only within the HH in HH vs. HHL. Adult speakers made a noticeable contribution in this characteristic from the children. The result of the adult study was presented to confirm whether the children used a North Kyungsang dialect. With respect to individual speaker differences, the North Kyungsang children showed more or less consistent patterns in quantile-quantile plots for the HH vs. HHL, but for the HL vs. LHL and LH vs. LLH, there were more variations than for the HH vs. HHL. The individual speakers' variation was the largest for the HL vs. LHL and the smallest for HH vs. HHL. Considering these results, the effect of word length on f0 intervals tended to show pitch accent-type-specific characteristics in the process of prosodic acquisition.

• 음성과학
• /
• 제15권2호
• /
• pp.21-30
• /
• 2008

The current study investigated distributional properties of the Korean Accentual Phrase and their implication to word segmentation. The properties examined were the frequency of various AP tonal patterns, the types of tonal patterns that are imposed upon content words, and the average number and temporal location of content words within the AP. A total of 414 sentences from the Read speech corpus and the Radio corpus were used for the data analysis. The results showed that the 84% of the APs contained one content word, and that almost 90% of the content words are located in AP-initial position. When the AP-initial onset was not an aspirated or tense consonant, the most common AP patterns were LH, LHH, and LHLH (78%), and 88% of the multisyllabic content words start with a rising tone in AP-initial position. When the AP-initial onset was an aspirated or tense consonant, the most common AP patterns were HH, HHLH, and HHL (72%), and 74% of the multisyllabic content words start with a level H tone in AP-initial position. The data further showed that 84.1% of APs end with the final H tone. The findings provide valuable information about the prosodic pattern and structure of Korean APs, and account for the results of a previous study which showed that Korean listeners are sensitive to AP-initial rising and AP-final high tones (Kim, 2007). This is in line with other cross-linguistic research which has revealed the correlation between prosodic probability and speech processing strategy.

• 한국시스템다이내믹스연구
• /
• 제12권1호
• /
• pp.131-153
• /
• 2011

The purpose of this study is to explore the applicability of the causal maps for estimating creativity. This study assumes that fluency, flexibility, originality and elaboration are elements of creativity; and there are common characteristics between systems and creative thinking. For this study, 30 students from the 5th grade create causal maps which are consisted of the contents of 'the water cycle in the earth'. The causal maps are analyzed and evaluated by focusing on the characteristics of creativity. In way of the marking causal maps based on creativity, each word is scored as 1 point on the basis of 30 points for fluency. Each word which is linked more than one word is scored 3 points for flexibility, but the maximum points are limited as 35 points. In originality, if it is approved each word is worthy as well as originality, it is scored as 10 points on the basis of 40 points. Lastly, each number of cycle loops is scored as 15 points for elaboration, and the maximum scores are limited as 45 points. As is stated above, the limiting of the maximum scores are designed based on corresponded to 10% students of participators. In the result of this study, the students' scores of evaluating creativity applied causal maps show similar patterns from relative point of view to the other results which were evaluated the creativity by credible organ. Consequently, it is recognized that the causal maps have the possibility of being able to estimate quantitatively the creativity.

• 대한음성학회지:말소리
• /
• 제31_32호
• /
• pp.51-82
• /
• 1996

The purpose of this paper is to gather pairs of heteronyms in Modem Korean and to propose that all of them should be differentiated in both the Hanngul orthography and Romanization as well as in the IPA transcription. More than a quarter of the whole Korean vocabulary consists of words with a long vowel and the number of minimal pairs distinguished only by the chroneme reaches nearly ten thousand (ie. twenty thousand words). It is suggested here that the letter s in Hanngul and the letter 'h' in the Roman alphabet be used to represent the long vowel. Another factor which brings forth lots of heteronyms in Korean is the lacking of enough indication as to non-automatic reinforcement in the initial consonant o( a word (or a morpheme) when following another within a phrase (or a word). It is proposed here that the non-automatincally rienforced word-initial consonant should be written with the letter h (like ㅺ, ㅼ, ㅽ, ㅾ) and an apostrophe (like 물'새 or 밭'이랑, 물'약) in Hanngul, and with the letter c and an apostrophe (like c'g-, c'd-, c'b-, c'j- ) in the Roman alphabet The morpheme-initial reinforced consonant within a word is written with the letters k, 1, p and cz for ㅺ, ㅼ, ㅽ, and ㅾ respectively. The contrasted pronunciations of pairs of heteronyms beginning with ㅁ/m sound are transcribed here for exemplification in the IPA, Roman alphabet and Hanngul.

• 음성과학
• /
• 제12권4호
• /
• pp.129-139
• /
• 2005

This paper investigates any possible correlation between the information structure and the occurrence of clause internal pauses in the spontaneous discourse. One of the possible functions of pause is its capacity to signal the information structure of the discourse. However, this aspect was not much explored in Korean spontaneous speech. In the present study, information structure of spontaneous speech was defined for each word or word group on the basis of the information structure analysis model proposed by Van Donzel (1999) and Roulet (1991, 1997). Thus, at a local level (words or word groups) of discourse structure, a distinction was made between three types of information, new, given and inferable. The results showed that clause internal pauses tend to appear more frequently before new information than other types of information. However compared to the total number of words or word groups it was not noticed any specific ordering concerning different kind of information status and pausing. It was however found that clause internal pauses did not appear randomly. The majority of them occurred at the initial part of the clause or the sentence. This tendency was mostly related to the division of sentence (or clause) into topic and comment. Thus, the role of pauses as a marker of information structure seems to be less effective in spontaneous discourse.

• 한국어교육
• /
• 제23권1호
• /
• pp.77-100
• /
• 2012

This study investigates issues in relation to text segmenting, in particular, line breaks in Korean language textbooks. Research on L1 and L2 reading has shown that readers process texts by chunking (grouping words into phrases or meaningful syntactic units) and, therefore, phrase-cued texts are helpful for readers whose syntactic knowledge has not yet been fully developed. In other words, it would be important for language textbooks to avoid awkward syntactic divisions at the end of a line, in particular, those textbooks for beginners and intermediate level learners. According to our analysis of a number of major Korean language textbooks for beginner-level learners, however, many textbooks were found to display line-breaks of awkward syntactic division. Moreover, some textbooks displayed frequent instances where a single word (or eojeol in the case of Korean) is split between different lines. This can hamper not only learners' learning of the rules of spaces between eojeols in Korean, but also learners' development in automatic word recognition, which is an essential part of reading processes. Based on the findings of our textbook analysis and of existing research on reading, this study suggests ways to overcome awkward line-breaks in Korean language textbooks.