• Title/Summary/Keyword: language training

Search Result 685, Processing Time 0.025 seconds

Performance Improvement of Context-Sensitive Spelling Error Correction Techniques using Knowledge Graph Embedding of Korean WordNet (alias. KorLex) (한국어 어휘 의미망(alias. KorLex)의 지식 그래프 임베딩을 이용한 문맥의존 철자오류 교정 기법의 성능 향상)

  • Lee, Jung-Hun;Cho, Sanghyun;Kwon, Hyuk-Chul
    • Journal of Korea Multimedia Society
    • /
    • v.25 no.3
    • /
    • pp.493-501
    • /
    • 2022
  • This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

Masking Level Difference: Performance of School Children Aged 7-12 Years

  • de Carvalho, Nadia Giulian;do Amaral, Maria Isabel Ramos;de Barros, Vinicius Zuffo;dos Santos, Maria Francisca Colella
    • Journal of Audiology & Otology
    • /
    • v.25 no.2
    • /
    • pp.65-71
    • /
    • 2021
  • Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

International Legal Measures of Protection of Critical Infrastructure Facilities in Banking Sphere

  • Oleg, Batiuk;Oleg, Novikov;Oleksandr, Komisarov;Natalia, Benkovska;Nina, Anishchuk
    • International Journal of Computer Science & Network Security
    • /
    • v.22 no.10
    • /
    • pp.145-154
    • /
    • 2022
  • Based on the obtained results of the study, the most problematic issues and legal conflicts are identified, which are related to the ratio of norms of domestic and foreign legislation, taking into account the requirements of the Constitution of Ukraine and the provisions of the Law of Ukraine "On international agreements". Along with this, it is stated in this scientific article that there are a number of provisions and examples of positive practice on the specified topic abroad and in international legal acts today, which should be used by Ukraine both in improving legislation on the issues of banking activity and in increasing the level of criminal legal protection of relevant critical infrastructure facilities, especially those that are substantively related to prevention and counteraction of activity, with regard to the legalization (laundering) of criminally obtained funds, financing of terrorism and the financing of the proliferation of weapons of mass destruction, which is quite relevant for our state, given the military conflict that is taking place on its territory in the Donbass. Again, in the same context, the need for more active cooperation between Ukraine and the FATF (international body developing a policy to combat money laundering) has been proven.

Masking Level Difference: Performance of School Children Aged 7-12 Years

  • de Carvalho, Nadia Giulian;do Amaral, Maria Isabel Ramos;de Barros, Vinicius Zuffo;dos Santos, Maria Francisca Colella
    • Korean Journal of Audiology
    • /
    • v.25 no.2
    • /
    • pp.65-71
    • /
    • 2021
  • Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

Ensuring the Quality of Higher Education in the United Kingdom Using Informatization

  • Andreikova, Iryna;Moiseienko, Natalia;Boichuk, Petro;Iliichuk, Liubomyra;Fedchenko, Karina;Bezliudnyi, Oleksandr;Sopivnyk, Ruslan
    • International Journal of Computer Science & Network Security
    • /
    • v.22 no.11
    • /
    • pp.324-330
    • /
    • 2022
  • The United Kingdom is known for the quality of its qualifications. There is a strict quality system with reputable bodies responsible for ensuring that high quality standards are met. In order for new qualifications to be accredited, they must meet all the requirements set out in the regulations for the quality and informatization of Education. The crucial role of the Agency for Quality Assurance of Higher Education (QAA) in the UK for creating high-quality management of higher education institutions is revealed, the influence of informatization tools on its effective mechanism as an independent entity is shown, and positive experience for the educational sector is highlighted. While the universities themselves are responsible for reviewing educational programs at the subject level, the QAA review focuses on verifying internal quality assurance, as well as systems and improvement strategies. The QAA uses a peer review process in which teams mostly consist of academic staff from other institutions to assess the quality of the institution's education. In Scotland, the team also includes an international reviewer. The student is also a member of the Scottish teams. In the UK, attention is paid to providing a cohort of experienced reviewers who can conduct high-quality monitoring and help with advice on improving education. All reviewers must complete training and have permission to participate in the review of educational programs. There are selected committees that are members of the QAA council, each of which is headed by a member of the Council or an independent person approved by the Council. Attention is drawn to the main areas of the QAA's work in the framework of environmental, social and corporate governance.

Ensuring the Quality of Higher Education in Ukraine

  • Olha, Oseredchuk;Mykola, Mykhailichenko;Nataliia, Rokosovyk;Olha, Komar;Valentyna, Bielikova;Oleh, Plakhotnik;Oleksandr, Kuchai
    • International Journal of Computer Science & Network Security
    • /
    • v.22 no.12
    • /
    • pp.146-152
    • /
    • 2022
  • The National Agency for Quality Assurance in Higher Education plays a crucial role in education in Ukraine, as an independent entity creates and ensures quality standards of higher education, which allow to properly implement the educational policy of the state, develop the economy and society as a whole. The purpose of the article: to reveal the crucial role of the National Agency for Quality Assurance in Higher Education to create quality management of higher education institutions, to show its mechanism as an independent entity that creates and ensures quality standards of higher education. and society as a whole. The mission of the National Agency for Quality Assurance in Higher Education is to become a catalyst for positive changes in higher education and the formation of a culture of its quality. The strategic goals of the National Agency are implemented in three main areas: the quality of educational services, recognition of the quality of scientific results, ensuring the systemic impact of the National Agency. The National Agency for Quality Assurance in Higher Education exercises various powers, which can be divided into: regulatory, analytical, accreditation, control, communication. The effectiveness of the work of the National Agency for Quality Assurance in Higher Education for 2020 has been proved. The results of a survey conducted by 183 higher education institutions of Ukraine conducted by the National Agency for Quality Assurance in Higher Education are shown. Emphasis was placed on the development of "Recommendations of the National Agency for Quality Assurance in Higher Education regarding the introduction of an internal quality assurance system." The international activity and international recognition of the National Agency for Quality Assurance in Higher Education are shown.

Re-defining Named Entity Type for Personal Information De-identification and A Generation method of Training Data (개인정보 비식별화를 위한 개체명 유형 재정의와 학습데이터 생성 방법)

  • Choi, Jae-hoon;Cho, Sang-hyun;Kim, Min-ho;Kwon, Hyuk-chul
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.206-208
    • /
    • 2022
  • As the big data industry has recently developed significantly, interest in privacy violations caused by personal information leakage has increased. There have been attempts to automate this through named entity recognition in natural language processing. In this paper, named entity recognition data is constructed semi-automatically by identifying sentences with de-identification information from de-identification information in Korean Wikipedia. This can reduce the cost of learning about information that is not subject to de-identification compared to using general named entity recognition data. In addition, it has the advantage of minimizing additional systems based on rules and statistics to classify de-identification information in the output. The named entity recognition data proposed in this paper is classified into twelve categories. There are included de-identification information, such as medical records and family relationships. In the experiment using the generated dataset, KoELECTRA showed performance of 0.87796 and RoBERTa of 0.88.

  • PDF

A Study on the Digital Therapeutics Based Community Care for Rehabilitation in Dysarthria in the Post-COVID-19 Era (Post-COVID-19 시대 마비말장애 재활을 위한 디지털 치료제 기반의 커뮤니티케어 방안)

  • Lee, Sang-Do
    • Journal of the Korea Convergence Society
    • /
    • v.13 no.1
    • /
    • pp.313-323
    • /
    • 2022
  • The purpose of this study was to explore ways a digital therapeutics-based community care plans for the rehabilitation in dysarthria in a situation where non-face-to-face services are expanding in the COVID-19 era. To this end, a qualitative study was conducted on experts working in hospitals, speech-language pathology centers, and social welfare centers, and as a result of the study, 3 topics, 9 sub-themes, and 18 content units were derived. Based on the analysis results, the digital therapeutics-based community care model consisted of 9 types: remote diagnosis, telepractice, rehabilitation training program, peer supporters, clinical support, communication, psychosocial intervention, and care plan services. This study will be able to provide basic data for health care & welfare services using digital therapeutics and guidelines for establishing shared care plans based on multidisciplinary cooperation.

Analyzing the Child Care Practicum Experience of Foreign Students: Exploring Challenges and Benefits (외국인 유학생의 보육실습 경험 분석: 어려움과 가치를 중심으로)

  • Jeongwon Kang;Soyoung Kook;Myungeum Park
    • Korean Journal of Childcare and Education
    • /
    • v.19 no.3
    • /
    • pp.19-39
    • /
    • 2023
  • Objective: The purpose of this study was to analyze the experiences of foreign students in childcare practicum, with a specific focus on identifying the difficulties they encountered and the values they derived from their practicum experiences. The aim was to gain insights that can contribute to improving practicum support for these students. Methods: A total of 6 foreign students were selected as participants for this study using snowball sampling. The data collection period spanned from May 2021 to March 2023, during which semi-structured interviews were conducted and qualitatively analyzed. Results: Foreign students faced challenges in securing practicum placements prior to the start of their program. Communication difficulties necessitated the use of interpreters to interact with children. Additionally, documenting information in a language other than their mother tongue posed a challenge. Consequently, there was a need for tailored training support to address the specific needs of foreign students in childcare practicum. Despite these challenges, the students reported rewarding and valuable experiences during their practicum. These experiences included discovering the teaching identity in Korea, learning about desirable practices in the field, recognizing and addressing personal shortcomings, and developing a sense of vocation for the advancement of infant education in their home countries. Conclusion/Implications: If we actively listen to and provide appropriate support for the specific needs of foreign students in their childcare practicum, they have the potential to become excellent childcare teachers who can foster a harmonious and inclusive environment within our multicultural society.

Fine-tuning of Attention-based BART Model for Text Summarization (텍스트 요약을 위한 어텐션 기반 BART 모델 미세조정)

  • Ahn, Young-Pill;Park, Hyun-Jun
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1769-1776
    • /
    • 2022
  • Automatically summarizing long sentences is an important technique. The BART model is one of the widely used models in the summarization task. In general, in order to generate a summarization model of a specific domain, fine-tuning is performed by re-training a language model trained on a large dataset to fit the domain. The fine-tuning is usually done by changing the number of nodes in the last fully connected layer. However, in this paper, we propose a fine-tuning method by adding an attention layer, which has been recently applied to various models and shows good performance. In order to evaluate the performance of the proposed method, various experiments were conducted, such as accumulating layers deeper, fine-tuning without skip connections during the fine tuning process, and so on. As a result, the BART model using two attention layers with skip connection shows the best score.