• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2133-2138
• /
• 2017

The analysis of existing XML documents and other documents was centered on words. It can be implemented using a morpheme analyzer, but it can classify many words in the document and cannot grasp the core contents of the document. In order for a user to efficiently understand a document, a paragraph containing a main word must be extracted and presented to the user. The proposed system retrieves keyword in the normalized XML document. Then, the user extracts the paragraphs containing the keyword inputted for searching and displays them to the user. In addition, the frequency and weight of the keyword used in the search are informed to the user, and the order of the extracted paragraphs and the redundancy elimination function are minimized so that the user can understand the document. The proposed system can minimize the time and effort required to understand the document by allowing the user to understand the document without reading the whole document.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.241-248
• /
• 2011

Homographs can have multiple senses. In order to understand the meaning of a sentence, it is necessary to identify which sense isused for each word in the sentence. Previous researches on this problem heavily relied on the word co-occurrence information. However, we noticed that in case of verbs, information about subordinating cases of verbs can be utilized to further improve the performance of word sense disambiguation. Different senses require different sets of subordinating cases. In this paper, we propose the verb sense disambiguation using subordinating case information. The case information acquire postposition features in Standard Korean Dictionary. Our experiment on 12 high-frequency verb homographs shows that adding case information can improve the performance of word sense disambiguation by 1.34%, from 97.3% to 98.7%. The amount of improvement may seem marginal, we think it is meaningful because the error ratio reduced to less than a half, from 2.7% to 1.3%.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.2
• /
• pp.279-284
• /
• 2014

Purpose: This study will be a basic research providing data which can reduce eye strain using monitor and electric media by measuring legibility of text color on monitor. Methods: Total experimental subjects who don't have color anomaly and best corrected visual acuity was over 1.0 were 50 and their mean age was $22.83{\pm}1.47$. Reading speed test were carried out with 163 words and subjects who could read over 123 words were selected for legibility examination. Monitor background color was white and letter colors were black, blue, red, and yellow for the legibility examination. Results: In case of text color of black, blue, red, and yellow, Event duration(sec) was measured to 41.89, 42.89, 45.32, and 56.28, respevtively, and reading error (number) was measured to 1.94, 2.74, 3.36, and 5.14. Average of fixation duration(sec) was measured to 0.25, 0.26, 0.27, and 0.32. Conclusions: In this paper, event Duration, reading error and average of fixation duration which can measure the legibility was reduced in a sequence of black blue, red, and yellow.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.203-211
• /
• 2020

Given that American English and British English show differences for several vowels and that Korean students have mainly been exposed to American English, this study examined 27 Korean university students' identification of American and British English vowels. The results showed that Korean students' identification accuracy of American English vowels was higher (64.7%) than that of British English (54.7%), thus indicating that Korean students' familiarity with American English affected the students' identification of English vowels. However, vowel variation also affected students' identification of English vowels in that only the American English vowels in the words beat, bat, but, burt, bart, bite were better identified than the corresponding vowels in British English. Among the vowels which exhibit differences between American English and British English, the students' identification accuracy of the American English vowels in burt, bart, bat was significantly higher than that of British English and the error patterns for these vowels were also different. The analysis of vowel error patterns indicated that Korean students had much difficulty with non-rhotic vowels and [a] in bat in British English. Further, the vowels in bot and boat demonstrated a similar [ɑ]-[ɔ]-[ʌ] confusion and also a confusion between rounded vowels in spite of the differences of these vowels between American English and British English. Some pedagogical implications for teaching of English vowels were discussed based on the findings of the present study.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.783-787
• /
• 2012

It is not easy to find out syntactic error in a spelling checker systems of Korean, because the spelling checker is generally to correct each phrase and it cannot check the errors of contextual ill-matched words. Spelling checker system tests errors based on a words. Disambiguation of lexical ambiguities is important in natural language processing. Its outputs is used in syntactic analysis. For accurate analysis of a sentence, syntactic analysis system must find out the ambiguity of morphemes in a word. In this paper, we suggest several rules to resolve the ambiguities of morphemes in a word. Using these methods, we can reduce many lexical ambiguities in Korean.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1
• /
• pp.86-91
• /
• 1999

This paper presents the text-prompt method to overcome the weakness of text-dependent and text-independent speaker recognition. Enhanced dynamic time warping for speaker recognition algorithm is applied. For the real-time processing, we use a simple algorithm for end-point detection without increasing computational complexity. The test shows that the weighted-cepstrum is most proper for speaker recognition among various speech parameters. As the experimental results of the proposed algorithm for three prompt words, the speaker identification error rate is 0.02%, and when the threshold is set properly, false rejection rate is 1.89%, false acceptance rate is 0.77% and verification total error rate is 0.97% for speaker verification.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.179-183
• /
• 2005

기존의 문서 재사용 탐지 모델은 문서 혹은 문장 단위로 그 내부의 단어 혹은 n-gram을 비교를 통해 문장의 재사용을 판별하였다. 그렇지만 문서 단위의 재사용 검사는 다른 문서의 일부분을 재사용하는 경우에 대해서는 문서 내에 문서 재사용이 이루어지지 않은 부분에 의해서 그 재사용 측정값이 낮아지게 되어 오류가 발생할 수 있는 가능성이 높아진다. 반면에 문장 단위의 문서 재사용 검사는 비교문서 내의 문장들에 대한 비교를 수행하게 되므로, 문서의 일부분에 대해 재사용물 수행한 경우에도 그 재사용된 부분 내의 문장들에 대한 비교를 수행하는 것이므로 문서 단위의 재사용에 비해 그런 경우에 더 견고하게 작동된다. 그렇지만, 문장 단위의 비교는 문서에 비해 짧은 문장을 단위로 하기 때문에 그 신뢰도에 문제가 발생하게 된다. 본 논문에서는 이런 문장단위 비교의 단점을 보완하기 위해 문장 단위의 문서 재사용 검사를 수행 후, 문장의 주변 문장의 재사용 검사 결과를 이용하여 문장 단위 재사용 검사에서 일어나는 오류를 감소시키고자 하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.25-30
• /
• 2023

초거대 언어모델은 과연 수수께끼 문제에 재치있는 답변을 할 수 있을까? 최근 초거대 언어모델(Large language model, LLM)은 강력한 성능 및 유저 만족도를 보이며 세계의 이목을 집중시키고 있다. 여러 태스크들에 대한 정량 평가를 넘어서 최근에는 LLM의 창의력 및 고도화된 언어능력을 평가하는 연구들이 등장하고 있다. 본 논문에서는 이러한 연구 흐름에 따라 LLM의 재치에 관해 고찰해본다. 이때 재치를 평가하기 위한 태스크로 이를 요구하는 말놀이인 수수께끼를 활용한다. 본 논문은 LLM이 수수께끼를 잘 수행하는지를 모델 추론을 통해 평가하며, 모델 추론 시 활용되는 프롬프트들의 성격에 따른 성능 변화를 관찰한다. 또한 수수께끼의 종류에 따른 모델의 능력을 비교 분석하며 LLM의 추론 결과에 대한 오류 분석을 수행한다. 본 논문은 실험을 통해 GPT-4가 가장 높은 성능을 보이며, 설명글이나 데이터 예시를 추가할 시 성능을 한층 더 향상시킬 수 있음을 확인한다. 또한 단어 기반보다는 특성 기반의 수수께끼에 더욱 강력한 성능을 보이며, 오류 유형 분석을 통해 LLM이 환각(hallucination) 문제와 창의력을 동시에 가지고 있다고 분석한다.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.1
• /
• pp.13-20
• /
• 2005

In this paper, I recognized Korean isolated words using CVEM which is suggested by M. Bilginer et al. CVEM is an algorithm which is easy to extract the common properties from training voice signals and also doesn't need complex calculation. In addition CVEM shows high accuracy in recognition results. But, CVEM has couple of problems which are impossible to use for many training voices and no discriminant information among extracted common vectors. To get the optimal common vectors from certain voice classes, various voices should be used for training. But CVEM is impossible to get continuous high accuracy in recognition because CVEM has a limitation to use many training voices and the absence of discriminant information among common vectors can be the source of critical errors. To solve above problems and improve recognition rate, k-clustering subspace method and DCVEM suggested. And did various experiments using voice signal database made by ETRI to prove the validity of suggested methods. The result of experiments shows improvements in performance. And with proposed methods, all the CVEM problems can be solved with out calculation problem.