• Korean Journal of Computational Design and Engineering
• /
• v.18 no.1
• /
• pp.28-35
• /
• 2013

Product Life cycle Management (PLM) is an indispensable tool for manufactures to develop competitive products in an efficient way. This enlarges the number of participants for product development who should understand PLM for their supporting activities. However, burdens for developing example products, maintaining complex PLM systems and training prerequisite skills for engineering tools such as CAD systems prohibit an efficient introductory course to PLM. This paper proposes a comprehensive introductory course to PLM that bases on general product development process. In addition, it enables participants to build their example products with familiar Lego blocks and to construct 3D CAD assembly models by using predefined 3D elements. The PLM system for the course provides an intuitive and simple user environment for participants to specify their parts lists, associated 3D CAD models, and product structure of example products. Experiences on a class of the course show it is a valid and efficient education and training method for the PLM introduction.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.424-427
• /
• 2022

본 연구는 도메인 특성이 강한 HR 평가문장을 BERT PLM 모델을통해 4 가지 class 로 구분하는 문제를 다룬다. 다양한 PLM 모델 적용과 training data 수에 따른 모델 성능 비교를 통해 특정 도메인에 언어모델을 적용하기 위해서 필요한 기준을 확인하였다. 또한 Unlabeled 된 HR 분야 corpus 를 활용하여 BERT 모델을 post-training 한 HR-BERT 가 PLM 분석모델 정확도 향상에 미치는 결과를 탐구한다. 위와 같은 연구를 통해 HR 이 가지고 있는 가장 큰 text data 에 대한 활용 기반을 마련하고, 특수한 도메인 분야에 PLM 을 적용하기 위한 가이드를 제시하고자 한다

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.191-206
• /
• 2022

Recently, it is a de-facto approach to utilize a pre-trained language model(PLM) to achieve the state-of-the-art performance for various natural language tasks(called downstream tasks) such as sentiment analysis and question answering. However, similar to any other machine learning method, PLM tends to depend on the data distribution seen during the training phase and shows worse performance on the unseen (Out-of-Distribution) domain. Due to the aforementioned reason, there have been many efforts to develop domain-specified PLM for various fields such as medical and legal industries. In this paper, we discuss the training of a finance domain-specified PLM for the Korean language and its applications. Our finance domain-specified PLM, KB-BERT, is trained on a carefully curated financial corpus that includes domain-specific documents such as financial reports. We provide extensive performance evaluation results on three natural language tasks, topic classification, sentiment analysis, and question answering. Compared to the state-of-the-art Korean PLM models such as KoELECTRA and KLUE-RoBERTa, KB-BERT shows comparable performance on general datasets based on common corpora like Wikipedia and news articles. Moreover, KB-BERT outperforms compared models on finance domain datasets that require finance-specific knowledge to solve given problems.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.388-392
• /
• 2023

개체 추출은 정보추출의 기초를 구성하는 태스크로, 관계 추출, 이벤트 추출 등 다양한 정보추출 태스크의 기반으로 중요하다. 최근에는 다중 레이블 개체와 중첩 개체를 다루기 위해 스팬기반의 개체추출이 주류로 연구되고 있다. 본 논문에서는 스팬을 표현하는 다양한 매핑과 자질들을 살펴보고 개체추출의 성능에 어떤 영향을 주는지를 분석하여 최적의 매핑 및 자질 조합을 제시하였다. 또한, 모델 구조에 있어서, 사전 학습 언어모델(PLM) 위에 BiLSTM 블록의 추가 여부에 따른 성능 변화를 분석하고, 모델의 학습에 있어서, 미세조정(finetuing) 이전에 예열학습(warmup training)을 사용하는 것이 효과적인지를 실험을 통해 비교 분석하여 제시하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.471-480
• /
• 2023

The Korean construction order volume in South Korea grew significantly from 91.3 trillion won in public orders in 2013 to a total of 212 trillion won in 2021, particularly in the private sector. As the size of the domestic and overseas markets grew, the scale and complexity of EPC (Engineering, Procurement, Construction) projects increased, and risk management of project management and ITB (Invitation to Bid) documents became a critical issue. The time granted to actual construction companies in the bidding process following the EPC project award is not only limited, but also extremely challenging to review all the risk terms in the ITB document due to manpower and cost issues. Previous research attempted to categorize the risk terms in EPC contract documents and detect them based on AI, but there were limitations to practical use due to problems related to data, such as the limit of labeled data utilization and class imbalance. Therefore, this study aims to develop an AI model that can categorize the contract terms based on the FIDIC Yellow 2017(Federation Internationale Des Ingenieurs-Conseils Contract terms) standard in detail, rather than defining and classifying risk terms like previous research. A multi-text classification function is necessary because the contract terms that need to be reviewed in detail may vary depending on the scale and type of the project. To enhance the performance of the multi-text classification model, we developed the ELECTRA PLM (Pre-trained Language Model) capable of efficiently learning the context of text data from the pre-training stage, and conducted a four-step experiment to validate the performance of the model. As a result, the ensemble version of the self-developed ITB-ELECTRA model and Legal-BERT achieved the best performance with a weighted average F1-Score of 76% in the classification of 57 contract terms.