• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.25-33
• /
• 2012

In this paper, we propose a rule-based model to correct errors in a speech recognition result in the mobile device environment. The proposed model considers the mobile device environment with limited resources such as processing time and memory, as follows. In order to minimize the error correction processing time, the proposed model removes some processing steps such as morphological analysis and the composition and decomposition of syllable. Also, the proposed model utilizes the longest match rule selection method to generate one error correction candidate per point, assumed that an error occurs. For the purpose of deploying memory resource, the proposed model uses neither the Eojeol dictionary nor the morphological analyzer, and stores a combined rule list without any classification. Considering the modification and maintenance of the proposed model, the error correction rules are automatically extracted from a training corpus. Experimental results show that the proposed model improves 5.27% on the precision and 5.60% on the recall based on Eojoel unit for the speech recognition result.

• Smart Media Journal
• /
• v.6 no.1
• /
• pp.16-21
• /
• 2017

Long time has passed since computers which used to be a means of research were commercialized and available for the general public. People used writing instruments to write before computer was commercialized. However, today a growing number of them are using computers to write instead. Computerized word processing helps write faster and reduces fatigue of hands than writing instruments, making it better fit to making long texts. However, word processing programs are more likely to cause spelling errors by the mistake of users. Spelling errors distort the shape of words, making it easy for the writer to find and correct directly, but those caused due to users' lack of knowledge or those hard to find may make it almost impossible to produce a document free of spelling errors. However, spelling errors in important documents such as theses or business proposals may lead to falling reliability. Consequently, it is necessary to conduct research on high-level spelling error correction programs for the general public. This study was designed to produce a system to correct sentence-level spelling errors to normal words with Korean alphabet similarity algorithm. On the basis of findings reported in related literatures that corrected words are significantly similar to misspelled words in form, spelling errors were extracted from a corpus. Extracted corrected words were replaced with misspelled ones to correct spelling errors with spelling error detection algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06a
• /
• pp.59-60
• /
• 2007

휴대폰과 메신저 등 통신 환경에서 사용되는 표준어가 아닌 SMS의 변형된 어휘 및 띄어쓰기 오류를 자동으로 교정하여 형태소 분석 및 품사 태깅의 성능 저하 문제를 방지하는 문자열 오류의 교정 방법을 제안하였다. 통신 어휘들의 문자열 사전 구축 방법으로 통신어휘집을 기반으로 수동으로 구축하는 방법과 수작업으로 구축된 말뭉치로부터 자동으로 변형된 문자열을 추출하는 방법, 그리고 문맥을 고려하는 방법을 비교-분석하고 실험 및 성능 평가 결과를 제시하였다.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.06a
• /
• pp.89-94
• /
• 2000

본 논문은 부산대 철자 검사/교정기의 기존 성능을 보완하고 기능을 추가하는데 중점을 두었다. 웹 문서, 신문 등을 통해서 사용자들이 자주 틀리는 오류 단어에 대해서 오류 유형을 분류했다. 이 결과를 철자 검사 및 교정 시스템에 적용하여 교정기법 개선을 통하여 띄어쓰기 교정 기능을 향상 시켰다. 이렇게 새로 구현한 시스템과 이전 시스템의 성능을 실험을 통해 비교 분석하였다. 본 연구를 진행하면서 발견한 문제점과 한계를 이후 더 발전 해야할 과제로 고찰하고 결론을 맺는다.

• Annual Conference on Human and Language Technology
• /
• 1992.10a
• /
• pp.459-468
• /
• 1992

문서 속에서 나타나는 철자 오류는 맞춤법을 몰라서 잘못 쓴 경우와 자료 입력 과정에서 잘못 입력된 경우로 볼 수 있다. 이들 각각의 오류들에 대해 맞춤법 및 표준어 규칙을 비롯하여 한국어 자료의 통계적 분석을 통한 교정 기법을 제공하고자 한다. 본 논문은 철자 검사기가 틀리다고 판단한 오류 어절로부터 올바른 어절을 찾아서 교정해 주고 철자가 틀린 원인을 알려줄 수 있는 도움말 기능을 제공하는 철자 교정 시스템을 구현하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.446-449
• /
• 2020

최근 성공적인 문법 오류 교정 연구들에는 복잡한 인공신경망 모델이 사용되고 있다. 그러나 이러한 모델을 훈련할 수 있는 공개 데이터는 필요에 비해 부족하여 과적합 문제를 일으킨다. 이 논문에서는 적대적 훈련 방법을 적용해 문법 오류 교정 분야의 과적합 문제를 해결하는 방법을 탐색한다. 모델의 비용을 증가시키는 경사를 이용한 fast gradient sign method(FGSM)와, 인공신경망을 이용해 모델의 비용을 증가시키기 위한 변동을 학습하는 learned perturbation method(LPM)가 실험되었다. 실험 결과, LPM은 모델 훈련에 효과가 없었으나, FGSM은 적대적 훈련을 사용하지 않은 모델보다 높은 F_0.5 성능을 보이는 것이 확인되었다.

• Journal of Elementary Mathematics Education in Korea
• /
• v.20 no.3
• /
• pp.457-477
• /
• 2016

The purpose of this study is to analyze and diagnose the type of errors indicated by the students in the process of calculation of the fractional multiplication and division, and to propose teaching methods, to effectively correct errors. The results obtained through this study are as follows. First, based on the results of the preliminary examination, 6 types of errors of the fractional multiplication and division has been organized. In particular, the most frequent types of errors are algorithm errors. Therefore, a teacher should explain the meaning and concept of fractional multiplication and division. Second, 4 prescription methods are proposed for understanding fractional multiplication and division. Third, according to the results of this study, it was effective to diagnose underachievers' error types and give corrective lesson according to the cause of the error types. Throughout the study, it's concluded that it is necessary to analyze and diagnose the error types of fractional multiplication and division, and then a teacher can correct error types by 4 proposed prescription methods. Also, 5 students showed interest while learning, and participated actively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.356-359
• /
• 2014

스마트 모바일 기기 즉, 스마트폰을 이용한 위치 기반 서비스(LBS)가 각광 받고 있는 가운데, 사용자 관점에서의 위치 측정에 대한 오류를 검출과 위치를 교정하는 서비스가 필요로 하게 되었다. GPS를 이용한 위치 측정의 방법을 예로 들어 GPS 신호를 수신하는 기기에서의 위치 측정 오류 감지는 어려운 실정이고 약간 더 정밀하게 측정하는 방법뿐이 존재하지 않는다. 이 논문에서는 GPS 수신기와 같은 사용자 관점에서 위치 데이터들의 속도를 계산하여 속도의 변화량을 이용해 multipath와 같은 위치 데이터의 오류를 검출하고 교정한 결과에 대해 다룬다. 단순 속도의 변화량이 아닌 인간의 이동 속도가 지수 확률 분포를 따른다는 사실을 기반하여 이동 윈도우(Moving Window)의 개념을 도입해 매 윈도우마다 한계 속도를 결정하고 한계 속도 이상의 속도가 발생하였을 때를 위치 오류라 검출 할 것이다.

• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.412-417
• /
• 2015

Context-sensitive spelling errors (CSSE) are hard to correct, since they are perfect words when analyzed alone. Determined only by considering the semantic and syntactic relations of their context, CSSEs affect largely the performance of spelling and grammar checkers. The existing Korean Spelling and Grammar Checker (KSGC 4.5) adopts a rule-based method, which uses hand-made correction rules for CSSEs. Using rule-based method, the KSGC 4.5 is designed to obtain the very high precision, which results in the extremely low recall. In this paper, we integrate our previous works that control the CSSE correction rules, in order to improve the recall without sacrificing the precision. In addition to the integration, facultative insertion of adverbs and conjugation suffix of predicates are also considered, as for constraint-loosening linguistic features.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.173-182
• /
• 2013

Typographical mistakes made in the writing process of drafts of electronic documents are more common than any other type of errors. The majority of these errors caused by mistyping are regarded as consequently still typo-errors, but a considerable number of them are developed into the grammatical errors and the semantic errors. Pseudo semantic errors among these errors due to typographical errors have more noticeable peculiarities than pure semantic errors between senses of surrounding context words within a sentence. These semantic errors can be detected and corrected by simple algorithm based on the co-occurrence frequency because of their prominent contextual discrepancy. I propose a method for detection and correction based on the co-occurrence frequency in order to detect semantic errors due to typo-errors. The co-occurrence frequency in proposed method is counted for only words with immediate dependency relation, and the cosine similarity measure is used in order to detect pseudo semantic errors. From the presented experimental results, the proposed method is expected to help improve the detecting rate of overall proofreading system by about 2~3%.