• East Asian mathematical journal
• /
• 제40권3호
• /
• pp.307-318
• /
• 2024

This paper explores the application of matrix factorization, specifically CUR decomposition, in the clustering of Korean language documents by topic. It addresses the unique challenges of Natural Language Processing (NLP) in dealing with the Korean language's distinctive features, such as agglutinative words and morphological ambiguity. The study compares the effectiveness of Latent Semantic Analysis (LSA) using CUR decomposition with the classical Singular Value Decomposition (SVD) method in the context of Korean text. Experiments are conducted using Korean Wikipedia documents and newspaper data, providing insight into the accuracy and efficiency of these techniques. The findings demonstrate the potential of CUR decomposition to improve the accuracy of document clustering in Korean, offering a valuable approach to text mining and information retrieval in agglutinative languages.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권4호
• /
• pp.145-152
• /
• 2020

기계독해는(Machine reading comprehension) 사용자 질의와 관련된 문서를 기계가 이해한 후 정답을 추론하는 인공지능 자연어처리 태스크를 말하며, 이러한 기계독해는 챗봇과 같은 자동상담 서비스에 활용될 수 있다. 최근 자연어처리 분야에서 가장 높은 성능을 보이고 있는 BERT 언어모델은 대용량의 데이터를 pre-training 한 후에 각 자연어처리 태스크에 대해 fine-tuning하여 학습된 모델로 추론함으로써 문제를 해결하는 방식이다. 본 논문에서는 BERT기반 특허상담 기계독해 태스크를 위해 특허상담 데이터 셋을 구축하고 그 구축 방법을 소개하며, patent 코퍼스를 pre-training한 Patent-BERT 모델과 특허상담 모델학습에 적합한 언어처리 알고리즘을 추가함으로써 특허상담 기계독해 태스크의 성능을 향상시킬 수 있는 방안을 제안한다. 본 논문에서 제안한 방법을 사용하여 특허상담 질의에 대한 정답 결정에서 성능이 향상됨을 보였다.

• 방송공학회논문지
• /
• 제24권5호
• /
• pp.870-878
• /
• 2019

본 논문에서는 어텐션 알고리듬 (attention algorithm) 기반의 양방향성 LSTM (bidirectional long short-term memory; BLSTM) 을 동영상의 압축 표준을 예측하기 위해 사용한다. 자연어 처리 (natural language processing; NLP) 분야에서 순환적 신경망 (recurrent neural networks; RNN) 의 구조를 이용하여 문장의 다음 단어를 예측하거나 의미에 따라 문장을 분류하거나 번역하는 연구들은 계속되어왔고, 이는 챗봇, 음성인식 스피커, 번역 애플리케이션 등으로 상용화되었다. LSTM 은 RNN에서 gradient vanishing problem 을 해결하고자 고안됐고, NLP 분야에서 유용하게 사용되고 있다. 제안한 알고리듬은 BLSTM과 특정 단어에 집중하여 분류할 수 있는 어텐션 알고리듬을 자연어 문장이 아닌 동영상의 비트스트림에 적용해 동영상의 압축 표준을 예측하는 것이 가능하다.

• Communications for Statistical Applications and Methods
• /
• 제27권3호
• /
• pp.313-326
• /
• 2020

Deep Learning is the most important key to the development of Artificial Intelligence (AI). There are several distinguishable architectures of neural networks such as MLP, CNN, and RNN. Among them, we try to understand one of the main architectures called Recurrent Neural Network (RNN) that differs from other networks in handling sequential data, including time series and texts. As one of the main tasks recently in Natural Language Processing (NLP), we consider Neural Machine Translation (NMT) using RNNs. We also summarize fundamental structures of the recurrent networks, and some topics of representing natural words to reasonable numeric vectors. We organize topics to understand estimation procedures from representing input source sequences to predict target translated sequences. In addition, we apply multiple translation models with Gated Recurrent Unites (GRUs) in Keras on English-Korean sentences that contain about 26,000 pairwise sequences in total from two different corpora, colloquialism and news. We verified some crucial factors that influence the quality of training. We found that loss decreases with more recurrent dimensions and using bidirectional RNN in the encoder when dealing with short sequences. We also computed BLEU scores which are the main measures of the translation performance, and compared them with the score from Google Translate using the same test sentences. We sum up some difficulties when training a proper translation model as well as dealing with Korean language. The use of Keras in Python for overall tasks from processing raw texts to evaluating the translation model also allows us to include some useful functions and vocabulary libraries as well.

• 국제학술발표논문집
• /
• The 7th International Conference on Construction Engineering and Project Management Summit Forum on Sustainable Construction and Management
• /
• pp.291-296
• /
• 2017

Infrastructure development as national project suffers from social conflict which is one of main risk to be managed. Social conflicts have a negative impact on not only the social integration but also the national economy as they require enormous social costs to be solved. Against this backdrop, this study analyzes social conflict using articles published by online news media based on web-crawling and natural language processing (NLP) techniques. As an illustrative case, the Jeju Naval Base (JNB) project which is one of representative conflict case in South Korea is analyzed. Total of 21,788 articles and representative keywords are identified annually. Additionally, comparative analysis is conducted between the extracted keywords and actual events occurred during the project. The authors explain actual events in the JNB project based on the extracted words by the year. This study contributes to analyze social conflict and to extract meaningful information from unstructured data.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.613-616
• /
• 2018

Sequence tagging is an important task in Natural Language Processing (NLP), in which the Named Entity Recognition (NER) is the key issue. So far the most widely adopted model for NER in NLP is that of combining the neural network of bidirectional long short-term memory (BiLSTM) and the statistical sequence prediction method of Conditional Random Field (CRF). In this work, we improve the prediction accuracy of the BiLSTM by supporting an aligned word representation mechanism. We have performed experiments on multilingual (English, Spanish and Dutch) datasets and confirmed that our proposed model outperformed the existing state-of-the-art models.

• 한국산업융합학회 논문집
• /
• 제25권5호
• /
• pp.817-826
• /
• 2022

Patent information describes the history of technological progress in the relevant field, so it can be usefully used to identify trends in technological development and change and to establish R&D development strategies. This study proposes a method to identify the needs and problems of technology development at the planning stage of the R&D process and to analyze core technologies through patent analysis using Natural Language Processing(NLP) technology. As a big data source, collected patent documents registered in Google Patents for foldable technology, the latest technology in the display industry, and then extracted keywords using NLP analyzer. By classifying the extracted keywords into needs and problems for technology development, developed technology and materials, identified the needs of the market and customers and analyzed the technologies being researched and developed. Unlike previous studies that performed patent analysis, this methodology is different in that it can quickly and conveniently analyze the latest technology trends from big data called patents even if you do not have specialized knowledge and skills in the text mining. This study contributes to the digitalization of the R&D process based on data analysis.

• 한국정보통신학회논문지
• /
• 제27권1호
• /
• pp.41-46
• /
• 2023

최근, 빅데이터 분석은 기계학습의 발전에 따른 다양한 기법들을 이용할 수 있다. 현실에서 수집된 빅데이터는 단어 간의 관계성에 대한 의미적 분석을 바탕으로 같거나 유사한 용어에 대한 자동화된 정제기법이 부족하다. 빅데이터는 일반적인 문장으로 기술되어 있다. 이러한 문제를 해결하기 위해 문장의 형태소 분석과 의미를 이해해야 할 필요가 있다. 이에 자연어를 분석하기 위한 기법인 NLP는 단어의 관계성과 문장을 이해할 수 있다. 본 논문에서는 빅데이터에서 추출된 문장에서 단어를 추출하여 단어 간의 연관 관계를 생성하는 방법을 연구한다. 이에 트랜스포머 기술을 이용한다.

• 정보관리학회지
• /
• 제23권2호
• /
• pp.167-183
• /
• 2006

본 연구는 이메일에 나타난 감성정보 메타데이터 추출에 있어 자연언어처리에 기반한 방식을 적용하였다. 투자분석가와 고객 사이에 주고받은 이메일을 통하여 개인화 정보를 추출하였다. 개인화란 이용자에게 개인적으로 의미 있는 방식으로 콘텐츠를 제공함으로써 온라인 상에서 관계를 생성하고, 성장시키고, 지속시키는 것을 의미한다. 전자상거래나 온라인 상의 비즈니스 경우, 본 연구는 대량의 정보에서 개인에게 의미 있는 정보를 선별하여 개인화 서비스에 활용할 수 있도록, 이메일이나 토론게시판 게시물, 채팅기록 등의 텍스트를 자연언어처리 기법에 의하여 자동적으로 메타데이터를 추출할 수 있는 시스템을 구현하였다. 구현된 시스템은 온라인 비즈니스와 같이 커뮤니케이션이 중요하고, 상호 교환되는 메시지의 의도나 상대방의 감정을 파악하는 것이 중요한 경우에 그러한 감성정보 관련 메타데이터를 자동으로 추출하는 시도를 했다는 점에서 연구의 가치를 찾을 수 있다.

• International Journal of Computer Science & Network Security
• /
• 제22권12호
• /
• pp.132-138
• /
• 2022

Due to the impacts of the current pandemic COVID-19 and the continuation of studying online. There is an urgent need for an effective and efficient education platform to help with the continuity of studying online. Therefore, the question bank system (QB) is introduced. The QB system is designed as a website to create a single platform used by faculty members in universities to generate questions and store them in a bank of questions. In addition to allowing them to add two types of questions, to help the lecturer create exams and present the results of the students to them. For the implementation, two languages were combined which are PHP and Python to generate questions by using Artificial Intelligence (AI). These questions are stored in a single database, and then these questions could be viewed and included in exams smoothly and without complexity. This paper aims to help the faculty members to reduce time and efforts by using the Question Bank System by using AI and Natural Language Processing (NLP) to extract and generate questions from given text. In addition to the tools used to create this function such as NLTK and TextBlob.