• Annual Conference on Human and Language Technology
• /
• 1992.10a
• /
• pp.491-501
• /
• 1992

변환 방식의 기계 번역에서 가장 중요한 부분은 변환 단계이며 여기서 변환사전이 매우 중요한 역활을 담당한다. 그러므로 인간이나 기계 번역기에 의해 생성되는 영어 문장은 이들이 가지고 있는 동사 사전의 내용과 효율적인 생성 알고리즘에 의해서 문장의 수준이나 정확성이 결정된다. 이렇게 생성된 문장을 검사하는 기존의 영어 문법 검사기들은 영어권의 사람들을 위주로 만들어졌기 때문에 문법적인 중요한 규정들을 포함하지 않고 있어서 비영어권의 사용자가 이용하기에는 부적절하다. 본 논문에서는 인간이 번역하였거나 기계 번역기에 의해 생성된 문장을 검사하고 교정할 수 있도록, 확장된 동사형을 기반으로 한 동사 사전을 제안하고 이를 이용한 영어 문장 검사기를 구현한다.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.311-328
• /
• 1992

The level and accuracy of English sentence that is generated by a man or machine translator are determined by the content of the verb dictionary and effective generation algorithm.The conventional English critiques is not adequate for foreigners because they do not have the verb dictionary including verb pattern or the important grammatical constraints. In this paper,Ipropose a structure of verb dictionary and an English sentence critique based on extended verb pattern that is useful to check and correct mistakes of English sentences generated by machine translator.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.293-299
• /
• 2021

본 논문은 외국어 학습을 위한 딥러닝 기반 영어 교육 플랫폼인 PEEP-Talk (Personalized English Education Platform)을 제안한다. PEEP-Talk는 딥러닝 기반 페르소나 대화 시스템과 영어 문법 교정 피드백 기능이 내장된 교육용 플랫폼이다. 또한 기존 페르소나 대화시스템과 다르게 대화의 흐름이 벗어날 시 이를 자동으로 판단하여 대화 주제를 실시간으로 변경할 수 있는 CD (Context Detector) 모듈을 제안하며 이를 적용하여 실제 사람과 대화하는 듯한 느낌을 사용자에게 줄 수 있다. 본 논문은 PEEP-Talk의 각 모듈에 대한 정량적인 분석과 더불어 CD 모듈을 객관적으로 판단할 수 있는 새로운 성능 평가지표인 CDM (Context Detector Metric)을 기반으로 PEEP-Talk의 강건함을 검증하였다. 이와 더불어 PEEP-Talk를 카카오톡 채널을 이용하여 배포하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.9-15
• /
• 2021

The current study examined the cyber learners' perceptions of the educational usefulness of Grammarly, an online grammar checker, after it was used to provide feedback to cyber university students in a situation where the instructor could not provide sufficient feedback on their written work in English. The survey results, revealed that the majority of learners had positive attitudes to the usefulness of Grammarly. In particular, the feedback immediately available whenever needed was regarded as helpful in improving English sentences, and most learners were highly satisfied with the amount of the feedback provided by Grammarly. It was also found that Grammarly had positive effects in terms of the affective domains, helping learners to improve their interest and confidence in English writing. In particular, Grammarly was found to be effective in reducing writing anxiety in English, one of the main factors negatively affecting writing performance in English. However, along with these positive results, limitations such as inaccurate feedback and inadequate explanation of errors were also found. Therefore, when Grammarly is used for English education, it is necessary to conduct multifaceted research to develop effective teaching methods that can minimize the problems that may arise from these limitations.

• 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.