• Title/Summary/Keyword: Generative Models

Search Result 180, Processing Time 0.023 seconds

Development of a Regulatory Q&A System for KAERI Utilizing Document Search Algorithms and Large Language Model (거대언어모델과 문서검색 알고리즘을 활용한 한국원자력연구원 규정 질의응답 시스템 개발)

  • Hongbi Kim;Yonggyun Yu
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.28 no.5
    • /
    • pp.31-39
    • /
    • 2023
  • The evolution of Natural Language Processing (NLP) and the rise of large language models (LLM) like ChatGPT have paved the way for specialized question-answering (QA) systems tailored to specific domains. This study outlines a system harnessing the power of LLM in conjunction with document search algorithms to interpret and address user inquiries using documents from the Korea Atomic Energy Research Institute (KAERI). Initially, the system refines multiple documents for optimized search and analysis, breaking the content into managable paragraphs suitable for the language model's processing. Each paragraph's content is converted into a vector via an embedding model and archived in a database. Upon receiving a user query, the system matches the extracted vectors from the question with the stored vectors, pinpointing the most pertinent content. The chosen paragraphs, combined with the user's query, are then processed by the language generation model to formulate a response. Tests encompassing a spectrum of questions verified the system's proficiency in discerning question intent, understanding diverse documents, and delivering rapid and precise answers.

Evaluating ChatGPT's Competency in BIM Related Knowledge via the Korean BIM Expertise Exam (BIM 운용 전문가 시험을 통한 ChatGPT의 BIM 분야 전문 지식 수준 평가)

  • Choi, Jiwon;Koo, Bonsang;Yu, Youngsu;Jeong, Yujeong;Ham, Namhyuk
    • Journal of KIBIM
    • /
    • v.13 no.3
    • /
    • pp.21-29
    • /
    • 2023
  • ChatGPT, a chatbot based on GPT large language models, has gained immense popularity among the general public as well as domain professionals. To assess its proficiency in specialized fields, ChatGPT was tested on mainstream exams like the bar exam and medical licensing tests. This study evaluated ChatGPT's ability to answer questions related to Building Information Modeling (BIM) by testing it on Korea's BIM expertise exam, focusing primarily on multiple-choice problems. Both GPT-3.5 and GPT-4 were tested by prompting them to provide the correct answers to three years' worth of exams, totaling 150 questions. The results showed that both versions passed the test with average scores of 68 and 85, respectively. GPT-4 performed particularly well in categories related to 'BIM software' and 'Smart Construction technology'. However, it did not fare well in 'BIM applications'. Both versions were more proficient with short-answer choices than with sentence-length answers. Additionally, GPT-4 struggled with questions related to BIM policies and regulations specific to the Korean industry. Such limitations might be addressed by using tools like LangChain, which allow for feeding domain-specific documents to customize ChatGPT's responses. These advancements are anticipated to enhance ChatGPT's utility as a virtual assistant for BIM education and modeling automation.

Performance Assessment of Machine Learning and Deep Learning in Regional Name Identification and Classification in Scientific Documents (머신러닝을 이용한 과학기술 문헌에서의 지역명 식별과 분류방법에 대한 성능 평가)

  • Jung-Woo Lee;Oh-Jin Kwon
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.19 no.2
    • /
    • pp.389-396
    • /
    • 2024
  • Generative AI has recently been utilized across all fields, achieving expert-level advancements in deep data analysis. However, identifying regional names in scientific literature remains a challenge due to insufficient training data and limited AI application. This study developed a standardized dataset for effectively classifying regional names using address data from Korean institution-affiliated authors listed in the Web of Science. It tested and evaluated the applicability of machine learning and deep learning models in real-world problems. The BERT model showed superior performance, with a precision of 98.41%, recall of 98.2%, and F1 score of 98.31% for metropolitan areas, and a precision of 91.79%, recall of 88.32%, and F1 score of 89.54% for city classifications. These findings offer a valuable data foundation for future research on regional R&D status, researcher mobility, collaboration status, and so on.

Analysis of deep learning-based deep clustering method (딥러닝 기반의 딥 클러스터링 방법에 대한 분석)

  • Hyun Kwon;Jun Lee
    • Convergence Security Journal
    • /
    • v.23 no.4
    • /
    • pp.61-70
    • /
    • 2023
  • Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

Development of a Multicultural Communication Assistant Application Utilizing Generative AI

  • Jung-hyun Moon;Ye-ram Kang;Da-eun Kim;Ga-kyung Lee;Jae-hoon Choi;Young-Bok Cho
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.8
    • /
    • pp.33-41
    • /
    • 2024
  • The continuous rise in the number of multicultural households and the issue of insufficient Korean language proficiency among marriage immigrants have highlighted the need to expand support programs for multicultural families and the importance of staffing multicultural centers. This paper designs and implements a diary application that leverages AI technology to enhance communication between parents and children in multicultural families based on diary entries. The proposed technology uses OCR, machine translation, Korean language correction, and sentiment analysis AI models to facilitate diary-based conversations between parents and children, addressing linguistic barriers and fostering emotional bonds. Additionally, it aims to provide direction for the development and harmony of future multicultural societies.

Multi-dimensional Contextual Conditions-driven Mutually Exclusive Learning for Explainable AI in Decision-Making

  • Hyun Jung Lee
    • Journal of Internet Computing and Services
    • /
    • v.25 no.4
    • /
    • pp.7-21
    • /
    • 2024
  • There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

3D Object Extraction Mechanism from Informal Natural Language Based Requirement Specifications (비정형 자연어 요구사항으로부터 3D 객체 추출 메커니즘)

  • Hyuntae Kim;Janghwan Kim;Jihoon Kong;Kidu Kim;R. Young Chul Kim
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.9
    • /
    • pp.453-459
    • /
    • 2024
  • Recent advances in generative AI technologies using natural language processing have critically impacted text, image, and video production. Despite these innovations, we still need to improve the consistency and reusability of AI-generated outputs. These issues are critical in cartoon creation, where the inability to consistently replicate characters and specific objects can degrade the work's quality. We propose an integrated adaption of language analysis-based requirement engineering and cartoon engineering to solve this. The proposed method applies the linguistic frameworks of Chomsky and Fillmore to analyze natural language and utilizes UML sequence models for generating consistent 3D representations of object interactions. It systematically interprets the creator's intentions from textual inputs, ensuring that each character or object, once conceptualized, is accurately replicated across various panels and episodes to preserve visual and contextual integrity. This technique enhances the accuracy and consistency of character portrayals in animated contexts, aligning closely with the initial specifications. Consequently, this method holds potential applicability in other domains requiring the translation of complex textual descriptions into visual representations.

A Study on Fine-Tuning and Transfer Learning to Construct Binary Sentiment Classification Model in Korean Text (한글 텍스트 감정 이진 분류 모델 생성을 위한 미세 조정과 전이학습에 관한 연구)

  • JongSoo Kim
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.28 no.5
    • /
    • pp.15-30
    • /
    • 2023
  • Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

Sentiment Analysis of News Based on Generative AI and Real Estate Price Prediction: Application of LSTM and VAR Models (생성 AI기반 뉴스 감성 분석과 부동산 가격 예측: LSTM과 VAR모델의 적용)

  • Sua Kim;Mi Ju Kwon;Hyon Hee Kim
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.5
    • /
    • pp.209-216
    • /
    • 2024
  • Real estate market prices are determined by various factors, including macroeconomic variables, as well as the influence of a variety of unstructured text data such as news articles and social media. News articles are a crucial factor in predicting real estate transaction prices as they reflect the economic sentiment of the public. This study utilizes sentiment analysis on news articles to generate a News Sentiment Index score, which is then seamlessly integrated into a real estate price prediction model. To calculate the sentiment index, the content of the articles is first summarized. Then, using AI, the summaries are categorized into positive, negative, and neutral sentiments, and a total score is calculated. This score is then applied to the real estate price prediction model. The models used for real estate price prediction include the Multi-head attention LSTM model and the Vector Auto Regression model. The LSTM prediction model, without applying the News Sentiment Index (NSI), showed Root Mean Square Error (RMSE) values of 0.60, 0.872, and 1.117 for the 1-month, 2-month, and 3-month forecasts, respectively. With the NSI applied, the RMSE values were reduced to 0.40, 0.724, and 1.03 for the same forecast periods. Similarly, the VAR prediction model without the NSI showed RMSE values of 1.6484, 0.6254, and 0.9220 for the 1-month, 2-month, and 3-month forecasts, respectively, while applying the NSI led to RMSE values of 1.1315, 0.3413, and 1.6227 for these periods. These results demonstrate the effectiveness of the proposed model in predicting apartment transaction price index and its ability to forecast real estate market price fluctuations that reflect socio-economic trends.

A study on the application of residual vector quantization for vector quantized-variational autoencoder-based foley sound generation model (벡터 양자화 변분 오토인코더 기반의 폴리 음향 생성 모델을 위한 잔여 벡터 양자화 적용 연구)

  • Seokjin Lee
    • The Journal of the Acoustical Society of Korea
    • /
    • v.43 no.2
    • /
    • pp.243-252
    • /
    • 2024
  • Among the Foley sound generation models that have recently begun to be studied, a sound generation technique using the Vector Quantized-Variational AutoEncoder (VQ-VAE) structure and generation model such as Pixelsnail are one of the important research subjects. On the other hand, in the field of deep learning-based acoustic signal compression, residual vector quantization technology is reported to be more suitable than the conventional VQ-VAE structure. Therefore, in this paper, we aim to study whether residual vector quantization technology can be effectively applied to the Foley sound generation. In order to tackle the problem, this paper applies the residual vector quantization technique to the conventional VQ-VAE-based Foley sound generation model, and in particular, derives a model that is compatible with the existing models such as Pixelsnail and does not increase computational resource consumption. In order to evaluate the model, an experiment was conducted using DCASE2023 Task7 data. The results show that the proposed model enhances about 0.3 of the Fréchet audio distance. Unfortunately, the performance enhancement was limited, which is believed to be due to the decrease in the resolution of time-frequency domains in order to do not increase consumption of the computational resources.