• 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.

• Korean Journal of Cognitive Science
• /
• v.17 no.4
• /
• pp.303-321
• /
• 2006

According to Harris'(1966) distributional hypothesis, understanding the meaning of a word is thought to be dependent on its context. Under this hypothesis about human language ability, this paper proposes a computational model for native speaker's language processing mechanism concerning word sense disambiguation, based on two sets of experiments. Among the three computational models discussed in this paper, namely, the logic model, the probabilistic model, and the probabilistic inference model, the experiment shows that the logic model is first applied fer semantic disambiguation of the key word. Nexr, if the logic model fails to apply, then the probabilistic model becomes most relevant. The three models were also compared with the test results in terms of Pearson correlation coefficient value. It turns out that the logic model best explains the human decision behaviour on the ambiguous words, and the probabilistic inference model tomes next. The experiment consists of two pans; one involves 30 sentences extracted from 1 million graphic-word corpus, and the result shows the agreement rate anong native speakers is at 98% in terms of word sense disambiguation. The other pm of the experiment, which was designed to exclude the logic model effect, is composed of 50 cleft sentences.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.2
• /
• pp.174-182
• /
• 2002

The object-oriented design methods and their CASE tools are widely used in practice by many real-time software developers. However, object-oriented CASE tools require an additional step of identifying tasks from a given design model. Unfortunately, it is difficult to automate this step for a couple of reasons: (1) there are inherent discrepancies between objects and tasks; and (2) it is hard to derive tasks while maximizing real-time schedulability since this problem makes a non-trivial optimization problem. As a result, in practical object-oriented CASE tools, task identification is usually performed in an ad-hoc manner using hints provided by human designers. In this paper, we present a systematic, schedulability-aware approach that can help mapping real-time object-oriented models to multi-threaded implementations. In our approach, a task contains a group of mutually exclusive transactions that may possess different periods and deadline. For this new task model, we provide a new schedulability analysis algorithm. We also show how the run-time system is implemented and how executable code is generated in our frame work. We have performed a case study. It shows the difficulty of task derivation problem and the utility of the automated synthesis of implementations as well as the Inappropriateness of the single-threaded implementations.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.5
• /
• pp.379-387
• /
• 2006

The real world is spatially modelled conceptually either as discrete objects or earth surface. The generated data models are then usually represented as vector and raster respectively. Although there are limited cases where only one data model is sufficient to solve the spatial problem at hand, it is now generally accepted that GIS should be able to handle various types of data model. Recent advances in spatial technology introduced even more variety of heterogeneous data models and the need is ever growing to handle and manage efficiently these large variety of spatial data. The OGC (Open GIS Consortium), an international organization pursuing standardization in the geospatial industry. recently introduced the GMLJP2 (Geographic Mark-Up Language JP2) format which enables store and handle heterogeneous spatial data. The GMLJP2 format, which is based on the JP2 format which is an abbreviation for JPEG2000 wavelet image compression format, takes advantage of the versatility of the GML capabilities to add extra data on top of the compressed image. This study takes a close look into the GMLJP2 format to analyse and exploit its potential to handle and mange hetergeneous spatial data. Aerial image, digital map and LIDAR data were successfully transformed end archived into a single GMLJP2 file. A simple viewing program was made to view the heterogeneous spatial data from this single file.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.441-448
• /
• 2019

Previous researches on automatic spacing of Korean sentences has been researched to correct spacing errors by using n-gram based statistical techniques or morpheme analyzer to insert blanks in the word boundary. In this paper, we propose an end-to-end automatic word spacing by using deep neural network. Automatic word spacing problem could be defined as a tag classification problem in unit of syllable other than word. For contextual representation between syllables, Bi-LSTM encodes the dependency relationship between syllables into a fixed-length vector of continuous vector space using forward and backward LSTM cell. In order to conduct automatic word spacing of Korean sentences, after a fixed-length contextual vector by Bi-LSTM is classified into auto-spacing tag(B or I), the blank is inserted in the front of B tag. For tag classification method, we compose three types of classification neural networks. One is feedforward neural network, another is neural network language model and the other is linear-chain CRF. To compare our models, we measure the performance of automatic word spacing depending on the three of classification networks. linear-chain CRF of them used as classification neural network shows better performance than other models. We used KCC150 corpus as a training and testing data.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.2
• /
• pp.77-84
• /
• 2024

In the fourth industrial-revolution era, the construction industry is transitioning from traditional methods to digital processes. This shift has been challenging owing to the industry's employment of diverse processes and extensive human resources, leading to a gradual adoption of digital technologies through trial and error. One critical area of focus is the safety management at construction sites, which is undergoing significant research and efforts towards digitization and automation. Despite these initiatives, recent statistics indicate a persistent occurrence of accidents and fatalities in construction sites. To address this issue, this study utilizes large-scale language-model artificial intelligence to analyze big data from a construction safety-management information network. The findings are integrated into on-site models, which incorporate real-time updates from detailed design models and are enriched with location information and spatial characteristics, for enhanced safety management. This research aims to develop a big-data-driven safety-management platform to bolster facility and worker safety by digitizing construction-site safety data. This platform can help prevent construction accidents and provide effective education for safety practices.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.148-155
• /
• 2024

Despite the increasing importance of irony and sarcasm detection in the field of natural language processing, research on the Korean language is relatively scarce compared to other languages. This study aims to experiment with various models for irony detection in Korean text. The study conducted irony detection experiments using KoBERT, a BERT-based model, and ChatGPT. For KoBERT, two methods of additional training on sentiment data were applied (Transfer Learning and MultiTask Learning). Additionally, for ChatGPT, the Few-Shot Learning technique was applied by increasing the number of example sentences entered as prompts. The results of the experiments showed that the Transfer Learning and MultiTask Learning models, which were trained with additional sentiment data, outperformed the baseline model without additional sentiment data. On the other hand, ChatGPT exhibited significantly lower performance compared to KoBERT, and increasing the number of example sentences did not lead to a noticeable improvement in performance. In conclusion, this study suggests that a model based on KoBERT is more suitable for irony detection than ChatGPT, and it highlights the potential contribution of additional training on sentiment data to improve irony detection performance.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.127-138
• /
• 2021

The aim of this study is to demonstrate interaction as a describable field and tries to understand interaction from the perspective of attributes, thus building a theoretical to help interactive designer understand this field by common rule, rather than waste huge time and labor cost on iteration. Since the concept of interaction language has been brought out in 2000, there are varies of related academical studies, but all with defect such as proposed theoretical models are built on a non-uniform scale, or the analyzing perspective are mainly based on researcher's personal experience and being too unobjective. The value of this study is the clustered resource of research which mainly based on academical review. It collected 21 papers researched on interaction paradigm or interaction attributes published since 2000, extracting 19 interaction attribute models which contains 174 interaction attributes. Furthermore, these 174 attributes were re-clustered based on a more unified standard scale, and the two theoretical models summarized from it are respectively focuses on interaction control and interaction experience, both of which covered 6 independent attributes. The propose of this theoretical models and the analyzation of the cluster static will contribute on further revealing of the importance of interaction attribute, or the attention interaction attribute has been paid on. Also, in this regard, the interactive designer could reasonably allocate their energy during design process, and the future potential on various direction of interaction design could be discussed.