• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.215-218
• /
• 2005

This paper reports the current status of development of the Korean speech recognition platform (ECHOS). We implement new modules including ETSI feature extraction, backward search with trigram, and utterance verification. The ETSI feature extraction module is implemented by converting the public software to an object-oriented program. We show that trigram language modeling in the backward search pass reduces the word error rate from 23.5% to 22% on a large vocabulary continuous speech recognition task. We confirm the utterance verification module by examining word graphs with confidence score.

• Journal of Korean Medical classics
• /
• v.35 no.1
• /
• pp.155-172
• /
• 2022

Objectives : Contents on the 64 trigrams in major medical texts from early to late Joseon such as the Uibangyuchwi(醫方類聚), Donguibogam(東醫寶鑑), Somundaeyo(素問大要), Gyeokchigo(格致藁) were analyzed to examine their characteristics and historical context. Methods : Related contents in each medical texts were collected, sorted and analyzed for thorough examination. Results : The study of Changes which was widely applied in the field of medicine throughout the Joseon period focused more heavily on each of the trigram patterns, especially in regards to the qi interaction between the upper and lower axis of the body, rather than the various meanings of the ten wings[十翼]. This is a result of the Jing-Qi-Shen perspective of the body and the universe that transcends the Daoist inner cultivation method[內丹術], under which concepts related to qi circulation such as the opening and closing[闔闢] of the Heaven[乾] and the Earth[坤], the interaction between Water[水] and Fire[火] were considered more important. Conclusions : The historical context of the study of medicine and Changes[易] of Korea could be grasped through analysing the 64 trigrams in medical texts of each period in Joseon. Further research with the field of History of Changes studies is much anticipated.

• Lingua Humanitatis
• /
• v.7
• /
• pp.123-155
• /
• 2005

This paper concerns different forms of poetic thinking, each of which attempts to investigating truth of being on the ground of its idiosyncratic feature. The horizon evoked via these practices, however, is the Absolute where any plausibility of communication be fundamentally blocked off. Poetry, for instance, relinquishes its semantic auto-referentiality in order to be expressive of something unsayable. Poetic diction, coming-into-being, and sound with no meaning are those three expressive modes that I will examine in terms of the so-called "poetic thinking."

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.205-208
• /
• 2001

한글 혹은 영어 문자열을 입력할 때 입력 모드를 수동으로 전환하지 않더라도 입력된 문자열이 한글인지, 영어인지를 자동으로 판단하여 해당 문자열로 변환하는 방법을 제안한다. 한글 문자열일 확률을 계산하기 위해 음절 구성 요건과 음절 빈도 정보를 이용하고, 영어 문자열일 확률을 계산하기 위해 영어 bigram 및 trigram 정보를 이용한다. 또한, 한글과 영어가 혼합된 문자열은 한글일 확률과 영어일 확률이 교차되는 경계 위치를 인식함으로써 혼합 문자열을 생성한다.

• 중국학논총
• /
• no.55
• /
• pp.51-66
• /
• 2017

颐斋在『颐斋乱藁』中记录了自己对周易进行学习的内容.他从1760年(庚辰)32岁开始正式在白羊寺的众多庵堂里进行研读, 历经３年, 于1763年(癸未)7月23日离开白羊寺.之后, 他与金时粲, 徐命膺, 沈定镇, 韩晚裕, 李得显等人一起对周易进行了讨论, 并将自己的见解记录下来.他留下的注释书有 『皇极经世书解』 『朱子明筮赞解』, 『阳九阴六用数图』, 『经世天地始终之数图』, 『经世四象体用之数图』, 『易学啓蒙解』 等. 还有 『读易学啓蒙』, 『论易吟』, 『大易吟』 等３首与周易相关的诗.本论文则通过这３首诗对颐斋的周易特色进行阐明, 其特色大致可以概括为受容, 继承并发展了朱熹的主张.但他对周易的理解, 就像他所说的'通过象和数可以进行更好地理解'那样, 与义理相比, 他更关心象数, 实际上关于象数的注释和讨论也更多.因此, 虽说周易从象数易和义理学方面发展为图书易和儒家易, 并由朱熹完成了象数易和义理易的大统一, 但颐斋可以说则是一位以义理易和儒家易为基础, 十分看重象数易的易学者.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.18 no.6
• /
• pp.1558-1568
• /
• 2004

In ancient times, the society was unity of church and state and this social leader took medical treatment, too. As he ruled over a people with a Chinese classic on divination, many oriental doctors have considered that the medicine and a Chinese classic on divination(周易) have same origine, and have used it. The divination of six yinyang-strokes(六爻) must be made up of some established rules, for example, division of fifty sticks(葉蓍法), use of three coins(擲錢法), use of numbering sticks and number of time(時間作卦法). six yinyang-strokes is one trigram. As we divine good or bad luck through investigation of six yinyang-strokes, we can know good or bad luck of patient's diseases and cares. A purpose of divination is called use-spirit(用神), a spirit to weaken use-spirit is called dislike-spirit (忌神), and a spirit to help use-spirit is called pleasure-spirit(喜神). As use-spirit is a state of disease in divination of disease and patient, use-spirit is patient and dislike-spirit is disease. If supports of use-spirit are more than supports of dislike, it's good luck, but if not, it's bad luck. As use-spirit is a prognosis of disease in divination of care, use-spirit is patient, dislike-spirit is a state of disease, and pleasure-spirit are medicine and doctor. we inspect condition of patient with good or bad luck of use-spirit, state of disease with good or bad luck of dislike-spirit, and medicine with good or bad luck of pleasure-spirit. Finally, we take a bird's-eye-view of the balance of them and decide on course of action.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.4
• /
• pp.17-23
• /
• 2015

In this paper, we propose a mobile app clustering method using word clusters. Considering the quick change of mobile app trends, the proposed method divides the mobile apps into some semantically similar mobile apps by applying a clustering algorithm to the mobile app set, rather than the predefined category system. In order to alleviate the data sparseness problem in the short mobile app description texts, the proposed method additionally utilizes the unigram, the bigram, the trigram, the cluster of each word. For the purpose of accurately clustering mobile apps, the proposed method manages to avoid exceedingly small or large mobile app clusters by using the word clusters. Experimental results show that the proposed method improves 22.18% from 57.48% to 79.66% on overall accuracy by using the word clusters.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.345-352
• /
• 2006

The practical English-Korean machine translation system should be able to translate long sentences quickly and accurately. The intra-sentence segmentation method has been proposed and contributed to speeding up the syntactic analysis. This paper proposes the syntactic category prediction method using decision trees for getting accurate parsing results. In parsing with segmentation, the segment is separately parsed and combined to generate the sentence structure. The syntactic category prediction would facilitate to select more accurate analysis structures after the partial parsing. Thus, we could improve the parsing accuracy by the prediction. We construct features for predicting syntactic categories from the parsed corpus of Wall Street Journal and generate decision trees. In the experiments, we show the performance comparisons with the predictions by human-built rules, trigram probability and neural networks. Also, we present how much the category prediction would contribute to improving the translation quality.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.65-71
• /
• 2009

Natural language processing is necessary in order to efficiently perform filtering tremendous information produced in information retrieval of world wide web. This paper suggested an algorithm for meaning of numerals in the text. The algorithm for meaning of numerals utilized context-free grammars with the chart parsing technique, interpreted affixes connected with the numerals and was designed to disambiguate their meanings systematically supported by the n-gram based words. And the algorithm was designed to use POS (part-of-speech) taggers, to automatically recognize restriction conditions of trigram words, and to gradually disambiguate the meaning of the numerals. This research performed experiment for the suggested system of the numeral interpretation. The result showed that the frequency-proportional method recognized the numerals with 86.3% accuracy and the condition-proportional method with 82.8% accuracy.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.