• Progress in Superconductivity
• /
• v.4 no.1
• /
• pp.19-26
• /
• 2002

We have earlier developed a 40-channel SQUID system. An important figure of merit of a MEG system is the localization error, within which the underlying current source can be localized. With this system, we investigated the localization error in terms of the standard deviation of the coordinates of the ECDs and the systematic error due to inadequate modeling. To do this, we made localization of single current dipoles from tangential components of auditory evoked fields. Equivalent current dipoles (ECD) at N1m peak were estimated based on a locally fitted spherical conductor model. In addition, we made skull phantom and simulation measurements to investigate the contribution of various errors to the localization error. It was found that the background noise was the main source of the errors that could explain the observed standard deviation. Further, the amount of systematic error, when modeling the head with a spherical conductor, was much less than the standard deviation due to the background noise. We also demonstrated the performance of the system by measuring the evoked fields to grammatical violation in sentence comprehension.

• English Language & Literature Teaching
• /
• v.13 no.1
• /
• pp.111-131
• /
• 2007

This study explores teacher's corrective feedback types in an error treatment sequence in Korean EFL classroom setting. Corrective feedback moves are coded as explicit correction, recast, or initiations to self-repair. The frequency and distribution of each corrective feedback type are examined. But the special focus was given on feedback types eliciting learner's self-repair (clarification request, metalinguistic feedback, elicitation, and repetition of error) because initiations to self-repair are believed to facilitate language learning more than other strategies. The results of the study are as follows. First, there was an overwhelming tendency for teacher to use recasts whereas initiations to self-repair were not used as much as recast (52.4% vs. 29.5%). Second, the teacher tended to select feedback types in accordance with error types: namely, recasts after phonological, lexical, and translation errors and initiations to self-repair after grammatical errors though the differences were not significant. Finally, teacher's belief and students' expectation on corrective feedback were compared with actual corrective feedback representations respectively and some mismatches were found. Though both teacher and the students acknowledged the importance and necessity of self-repair, self-repair were not put into practice as such. Therefore, this study suggests more initiations to self-repair be used for effective language learning.

• Journal of KIISE:Software and Applications
• /
• v.35 no.6
• /
• pp.386-391
• /
• 2008

Some spoken word errors that violate grammatical or writing rules occurs frequently in communication environments like mobile phone and messenger. These unexpected errors cause a problem in a language processing system for many applications like speech recognition, text-to-speech translation, and so on. In this paper, we proposed and implemented an automatic correction system of ill-formed words and word spacing errors in SMS sentences that has been the major errors of poor accuracy. We experimented three methods of constructing the word correction dictionary and evaluated the results of those methods. They are (1) manual construction of error words from the vocabulary list of ill-formed communication languages, (2) automatic construction of error dictionary from the manually constructed corpus, and (3) context-dependent method of automatic construction of error dictionary.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.507-511
• /
• 2022

문법 교정 모델은 입력된 텍스트에 존재하는 문법 오류를 탐지하여 이를 문법적으로 옳게 고치는 작업을 수행하며, 학습자에게 더 나은 학습 경험을 제공하기 위해 높은 정확도와 재현율을 필요로 한다. 이를 위해 최근 연구에서는 문단 단위 사전 학습을 완료한 모델을 맞춤법 교정 데이터셋으로 미세 조정하여 사용한다. 하지만 본 연구에서는 기존 사전 학습 방법이 문법 교정에 적합하지 않다고 판단하여 문단 단위 데이터셋을 문장 단위로 나눈 뒤 각 문장에 G2P 노이즈와 편집거리 기반 노이즈를 추가한 데이터셋을 제작하였다. 그리고 문단 단위 사전 학습한 모델에 해당 데이터셋으로 문장 단위 디노이징 사전 학습을 추가했고, 그 결과 성능이 향상되었다. 노이즈 없이 문장 단위로 분할된 데이터셋을 사용하여 디노이징 사전 학습한 모델을 통해 문장 단위 분할의 효과를 검증하고자 했고, 디노이징 사전 학습하지 않은 기존 모델보다 성능이 향상되는 것을 확인하였다. 또한 둘 중 하나의 노이즈만을 사용하여 디노이징 사전 학습한 두 모델의 성능이 큰 차이를 보이지 않는 것을 통해 인공적인 무작위 편집거리 노이즈만을 사용한 모델이 언어학적 지식이 필요한 G2P 노이즈만을 사용한 모델에 필적하는 성능을 보일 수 있다는 것을 확인할 수 있었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.211-219
• /
• 2019

Accomplishing information system, techniques, methodology have been studied continuously and give much help to auditors who are using them. Additionally audit report which is the conclusion of accomplishing ISA(information system audit), has law of a basis and phase with ITA/EA Law(Electronic Government Law). This paper is for better quality of ISA report. But it has more errors about sentence and Grammatical structures. In this paper, to achieve quality improvement objectives, it is necessary to recognize the importance of an audit report by investigating on objectives, functionality, structures and usability of a report firstly, and a legal basis, the presence of report next. Several types of audit reports were chosen and the reports errors were divided into several categories and analyzed. After grasping reasons of those errors, the methods for fixing those errors and check-lists model was provided. And based on that foundation, the effectiveness validation about real audit reports was performed. The necessity for efforts to improve the quality of audit reports was emphasized and further research subject(AI Automatic tool) of this paper conclusion. We also expect this paper to be useful for the organization to improve on ISA in the future.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.59-72
• /
• 2006

In the present study, we investigated the grammaticality judgement skills of children with developmental language impairments. The participants included 20 children with language impairments of ages ranging from 7 to 9 years and of IQ's ranging from 71 to 84, and 40 normally developing children. Twenty normal children were matched with the language impaired children in their language ages and the other 20 normal children were matched with the language impaired children in their chronological ages. The children were asked to judge the grammatical correctness of 48 short sentences, half of which were ungrammatical sentences containing incorrect case-markers and the other half were grammatically correct sentences. Four types of case-markers including nominative "i/ga", accusative "ul/lul", locative "e," and instrumental "ro" were systematically changed to generate the ungrammatical sentences. The language impaired children performed worse than both groups of normally developing children in detecting the ungrammatical sentences and in correcting the case-markers of those sentences. In detecting the errors of ungrammatical sentences, the language impaired children exhibited variable performances across the different case-markers.

• 중국학논총
• /
• no.70
• /
• pp.19-37
• /
• 2021

Foreign learners are not focusing on "적" grammar. Therefore, the lack of materials on "적" is the reason that foreign learners use "적" in real life. In particular, when teaching the Chinese-dependent noun "적", there are some problems in making the Chinese equivalent of "적". more accurately understood by Koreans. In addition, when using grammar through analyzing the grammatical conjunction centered on "적" and the corresponding expression of Chinese, the main reason for the error is that there is no common concept and form in the mother tongue, so there is no consciousness. Therefore, it is difficult for learners to learn similar expressions that are not in Chinese or Korean. Therefore, this study aims to improve specific educational programs for Korean learners and Korean Chinese learners in terms of the time system and the corresponding performance of Chinese grammar and Chinese characters based on the previous version of "적".

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.608-612
• /
• 2022

딥러닝의 발전 이후, 다양한 분야에서는 딥러닝을 이용해 이전에 어려웠던 작업들을 해결하여 사용자에게 편의성을 제공하고 있다. 하지만 아직 딥러닝을 통해 이상적인 서비스를 제공하는 데는 어려움이 있다. 특히, 음성 인식 작업에서 음성 양식에서 이용 방안에 대하여 다양성을 제공해주는 음성을 텍스트로 전환하는 Speech-To-Text(STT)은 문장 결과가 이상치에 달하지 못해 오류가 나타나게 된다. 본 논문에서는 STT 결과 보정을 문법 교정으로 치환하여 종단에서 올바른 토큰들을 조합하여 성능 향상을 하기 위해 각 토큰 별 품질 평가를 진행하는 모델을 한국어에서 적용하고 성능의 향상을 확인한다.

• 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.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.488-491
• /
• 2019

문법 오류 교정은 문법적으로 오류가 있는 문장을 입력 받아 오류를 교정하는 시스템이다. 문법 오류 교정을 위해서는 문법 오류를 제거하는 것과 더불어 자연스러운 문장을 생성하는 것이 중요하다. 이 연구는 적대적 생성 신경망(GAN)을 이용하여 정답 문장과 구분이 되지 않을 만큼 자연스러운 문장을 생성하는 것을 목적으로 한다. 실험 결과 GAN을 이용한 문법 오류 교정은 MaxMatch F_0.5 score 기준으로 0.4942을 달성하여 Baseline의 0.4462보다 높은 성능을 기록했다.