• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.69-71
• /
• 2021

특허분야에서 자연어처리 태스크는 특허문헌의 언어적 특이성으로 문제 해결의 난이도가 높은 과제임에 따라 한국 특허문헌에 최적화된 언어모델의 연구가 시급한 실정이다. 본 논문에서는 대량의 한국 특허문헌 데이터를 최적으로 사전 학습(pre-trained)한 Korean Patent ELECTRA 모델과 tokenize 방식을 제안하며 기존 범용 목적의 사전학습 모델과 비교 실험을 통해 한국 특허문헌 자연어처리에 대한 발전 가능성을 확인하였다.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• The Korean Journal of Archival Studies
• /
• no.68
• /
• pp.41-72
• /
• 2021

In order to analyze big data, documents should be converted to a open standard format to increase machine readability. It also need natural language processing tools. This study focused on the background of intelligent document processing and the status of research in the public sector, and predicted the changes in work that intelligent document processing would bring. This study noted the changes that intelligent document processing would bring to the archival work, and also considered changes in the role of archivist and their required competencies. Changes in archival work could be anticipated across a wide range of Records Management work and Archives Management work. In particular, it was expected to have a significant impact on the automation of repetitive archival tasks or the description and utilization of records. This study proposed the need to prepare new archival work procedures, methods, and necessary competencies in response to these change in archival work.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.321-322
• /
• 2022

스마트폰 사용자가 늘어남에 따라 갖춰줘야 할 보안성이 취약하여, 다양한 바이러스 및 악성코드 위험에 노출되어 있다. 안드로이드는 운영체제 중 가장 많이 사용되는 운영체제로, 개방성이 높으며 수많은 악성 앱 및 바이러스가 마켓에 존재하여 위험에 쉽게 노출된다. 2년 넘게 이어진 코로나 바이러스(Covid-19)으로 인해 꾸준히 위험도가 높아진 피싱공격(Phshing attack)은 현재 최고의 스마트폰 보안 위협 Top10에 위치한다. 본 논문에서는 딥러닝 기반 자연어처리 기술을 통해 피싱 공격 대응 방법 제안 및 실험 결과를 도출하고, 또한 향후 제안 방법을 보완하여 피싱 공격 및 다양한 모바일 보안 위협에 대응할 수 있는 앱을 설계할 것이다.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.33-39
• /
• 2021

Speech recognition technology is being combined with deep learning and is developing at a rapid pace. In particular, voice recognition services are connected to various devices such as artificial intelligence speakers, vehicle voice recognition, and smartphones, and voice recognition technology is being used in various places, not in specific areas of the industry. In this situation, research to meet high expectations for the technology is also being actively conducted. Among them, in the field of natural language processing (NLP), there is a need for research in the field of removing ambient noise or unnecessary voice signals that have a great influence on the speech recognition recognition rate. Many domestic and foreign companies are already using the latest AI technology for such research. Among them, research using a convolutional neural network algorithm (CNN) is being actively conducted. The purpose of this study is to determine the non-voice section from the user's speech section through the convolutional neural network. It collects the voice files (wav) of 5 speakers to generate learning data, and utilizes the convolutional neural network to determine the speech section and the non-voice section. A classification model for discriminating speech sections was created. Afterwards, an experiment was conducted to detect the non-speech section through the generated model, and as a result, an accuracy of 94% was obtained.

• Information Systems Review
• /
• v.21 no.1
• /
• pp.23-38
• /
• 2019

The social network service (SNS) is one of the important marketing channels, so many companies actively exploit SNSs by posting SNS messages with appropriate content and style for their customers. In this paper, we focused on the psychological distances embedded in the SNS messages and developed a method to measure the psychological distance in SNS message by mixing a traditional content analysis, natural language processing (NLP), and machine learning. Through a traditional content analysis by human coding, the psychological distance was extracted from the SNS message, and these coding results were used for input data for NLP and machine learning. With NLP, word embedding was executed and Bag of Word was created. The Support Vector Machine, one of machine learning techniques was performed to train and test the psychological distance in SNS message. As a result, sensitivity and precision of SVM prediction were significantly low because of the extreme skewness of dataset. We improved the performance of SVM by balancing the ratio of data by upsampling technique and using data coded with the same value in first content analysis. All performance index was more than 70%, which showed that psychological distance can be measured well.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.704-713
• /
• 2014

Most natural language processing tasks depend on the outputs of some other tasks. Thus, they involve other tasks as subtasks. The main problem of this type of pipelined model is that the optimality of the subtasks that are trained with their own data is not guaranteed in the final target task, since the subtasks are not optimized with respect to the target task. As a solution to this problem, this paper proposes a consolidation of subtasks for a target task ($CST^2$). In $CST^2$, all parameters of a target task and its subtasks are optimized to fulfill the objective of the target task. $CST^2$ finds such optimized parameters through a backpropagation algorithm. In experiments in which text chunking is a target task and part-of-speech tagging is its subtask, $CST^2$ outperforms a traditional pipelined text chunker. The experimental results prove the effectiveness of optimizing subtasks with respect to the target task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.421-431
• /
• 2023

Nuclear power plants (NPPs) have technical specifications (Tech Specs) to ensure that the equipment and key operating parameters necessary for the safe operation of the power plant are maintained within limiting conditions for operation (LCO) determined by a safety analysis. The LCO of Tech Specs that identify the lowest functional capability of equipment required for safe operation for a facility must be complied for the safe operation of NPP. There have been previous studies to aid in compliance with LCO relevant to rule-based expert systems; however, there is an obvious limit to expert systems for implementing the rules for many situations related to LCO. Therefore, in this study, we present a retrieval methodology for similar LCO cases in determining whether LCO is met or not met. To reflect the natural language processing of NPP features, a domain dictionary was built, and the optimal term frequency-inverse document frequency variant was selected. The retrieval performance was improved by adding a Boolean retrieval model based on terms related to the LCO in addition to the vector space model. The developed domain dictionary and retrieval methodology are expected to be exceedingly useful in determining whether LCO is met.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.195-201
• /
• 2024

With the Covid-19(Corona Virus) spread all around the world, people are using this propaganda and the desperate need of the citizens to know the news about this mysterious virus by spreading fake news. Some Countries arrested people who spread fake news about this, and others made them pay a fine. And since Social Media has become a significant source of news, .there is a profound need to detect these fake news. The main aim of this research is to develop a web-based model using a combination of machine learning algorithms to detect fake news. The proposed model includes an advanced framework to identify tweets with fake news using Context Analysis; We assumed that Natural Language Processing(NLP) wouldn't be enough alone to make context analysis as Tweets are usually short and do not follow even the most straightforward syntactic rules, so we used Tweets Features as several retweets, several likes and tweet-length we also added statistical credibility analysis for Twitter users. The proposed algorithms are tested on four different benchmark datasets. And Finally, to get the best accuracy, we combined two of the best algorithms used SVM ( which is widely accepted as baseline classifier, especially with binary classification problems ) and Naive Base.