Kyungwoo Song

A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the

Infectious diseases spread rapidly, and epidemiological surveys are vital to detect high-risk transmitters and reduce transmission rates. To enhance efficiency and reduce the burden on epidemiologists, an automatic tool to assist with epidemiological surveys is necessary. This study aims to develop an automatic epidemiological survey to predict the influence of COVID-19-infected patients on future additional infections. To achieve this, the study utilized a dataset containing interaction informa

This paper introduces TC-Llama 2, a novel application of large language models (LLMs) in the technology-commercialization field. Traditional methods in this field, reliant on statistical learning and expert knowledge, often face challenges in processing the complex and diverse nature of technology-commercialization data. TC-Llama 2 addresses these limitations by utilizing the advanced generalization capabilities of LLMs, specifically adapting them to this intricate domain. Our model, based on th

Opinion mining is a technique extracting and analyzing people's opinions from online communities, and sentiment analysis is a kind of opinion mining analyzing attitudes of people toward an object, whether positive, negative, or neutral. Sentiment analysis has evolved alongside natural language processing models and applied to targets such as movie reviews. However, the performing arts have not been subjected to sentiment analysis as movie reviews, despite the apparent need for it. In this study,

Attention computes the dependency between representations, and it encourages the model to focus on the important selective features. Attention-based models, such as Transformer and graph attention network (GAT), are widely utilized for sequential data and graph-structured data. This paper suggests a new interpretation and generalized structure of the attention in Transformer and GAT. For the attention in Transformer and GAT, we derive that the attention is a product of two parts: 1) the RBF kern

This paper describes a methodology to predict a future state of unknown high-speed vehicles by applying machine learning techniques. Traditionally, the state estimation of high-speed vehicles is carried out by the variations of Kalman filters, but such state estimation is limited to the temporal moment of the observation. Therefore, the future state of high-speed vehicles has been obtained through a number of predictive iterations with a dynamics equation. This dynamic equation requires a key pa

Disasters and responses have evolved over-time, and the evolution has been affected by various factors, such as societal change, climate change, and technological advance. To better prepare the future disasters, we need to estimate the evolution trend of the past disasters and the responses. This paper analyzes the academic articles of the field with network-text analyses. The analyses captured the word level and the topic level evolution over-time with statistical significance tests. Further, w

Understanding politics is challenging because the politics take the influence from everything. Even we limit ourselves to the political context in the legislative processes; we need a better understanding of latent factors, such as legislators, bills, their ideal points, and their relations. From the modeling perspective, this is difficult 1) because these observations lie in a high dimension that requires learning on low dimensional representations, and 2) because these observations require com