Welcome to Yongshin's page
I graduated with an M.S. from the Graduate School of Data Science at KAIST, where I was a member of the Interactive Computing Lab under the guidance of Prof. Uichin Lee. My master’s research focused on predicting human emotion using audio and physiological signals, specifically analyzing how the counterpart’s data positively influences the speaker’s emotion prediction during naturalistic conversations.
Previously, I worked as a machine learning engineer at Okestro, where I specialized in Natural Language Processing (NLP). Our team was dedicated to automating corporate analysis in the field of business intelligence using NLP. We developed a service for real-time company evaluation in a cloud environment. We also explored generative models, including the use of Retrieval-Augmented Generation to create a domain-specific chatbot. In addition, we worked on a project to finetuned an open-source gpt model such as Llama, Orion to improve the RAG inference ability for GPT.
I am currently employed at KPMG as a senior consultant, focusing on the development of an AI platform that offers a range of AI technologies such as Natural Language Understanding (NLU) and Natural Language Generation (NLG) to our clients.
Outside of my professional life, I enjoy staying active through sports, particularly racket games like badminton and tennis. I also find relaxation in playing Go, a game that, despite its simple rules, requires deep strategic thinking. I am known for my consistency and commitment, always striving to approach tasks with responsibility and dedication.
Projects
- Yongshin Kim, Taehee Lee, Sanghyeon Jung, Chanjae Lee, Taewan Kwon, “Improving Cloud FAQ Experience through Contrastive Learning-based Inquiry Classification”, Korea Computer Congress, Jeju Island, Korea (2023)
- [PPT] KCC 2023
- Taewan Kwon, Chanjae Lee, Sanghyeon Jung, Yongshin Kim, Taehee Lee, “Framework for Log-Level Anomaly Detection in a Log Sequence using Bidirectional Encoder Representations from Transformers”, Korea Computer Congress, Jeju Island, Korea (2023)
- Yongshin Kim, Sanghyeon Jung, Chanjae Lee, Jinhee Kim, “Baseline of SWOT Classification using Bidirectional Encoder Representations from Transformers for Business Intelligence Cloud Platform”, Korean Institute of Information Technology, 2022 Fall Conference, Jeju Island, Korea (2022)
- [PPT] SWOT
- Sanghyeon Jung, Yongshin Kim, Kwangpil Jeong, Taehee Lee, Taewan Kwon, “Automation of Company SWOT Analysis Using Sentence BERT”, Korean Institute of Information Technology, 2022 Fall Conference, Jeju Island, Korea (2022)
- Yongshin Kim, “Improving Multi-modal Emotion Recognition with Counterpart Data in Dyadic Conversations”, Master thesis, 2022 Spring
- [PPT] Master Defense
- Yongshin Kim, Panyu Zhang, Gyuwon Jung, Heepyung Kim, Uichin Lee, “Causal Analysis of Observational Mobile Sensor Data: A Comparative Study”, Korea Computer Congress, 2021 Spring Conference, Jeju Island, Korea (2021)
- [PPT] KCC 2021
- Peter Lee, Heepyung Kim, Yongshin Kim, Woohyeok Choi, M. Sami Zitouni, Ahsan Khandoker, Herbert F. Jelinek, Leontios Hadjileontiadis, Uichin Lee, Yong Jeong, “Beyond Pathogen Filtration: Possibility of Smart Mask as Wearable Device for Personal and Group Health and Safety Management”, Journal of Medical Internet Research, 2022
Experiences
I am currently employed at KPMG as a senior consultant, focusing on the development of an AI platform that offers a range of AI technologies such as Natural Language Understanding (NLU) and Natural Language Generation (NLG) to our clients.
I am currently working as a machine learning engineer studying NLP. Our team’s attention is directed towards generative models, particularly, the utilization of Retrieval-Augmented Generation to build a chatbot capable of responding to domain-specific queries. We are leveraging the langchain library to simplify this process. Furthermore, we are engaged in a project aimed at fine-tuning an open-source GPT model like llama to acquire expertise in our specific domain.
I participated in Digital Therapeutics(DTx), Smart mask, Contact tracing projects. Currently, I’m focusing on the DTx project to develop a platform that analyzes the effectiveness of digital treatments by studying and applying causal analysis techniques such as matching and CCM and also developing algorithms and interactive visualization platforms that use human biometric data to predict stress levels.
I worked as a general affairs director in the student government. I managed a budget of about 100 million won for student expenses and established and executed a large and small project funding plan. I also improved the maintenance and update of organizational documents, implementation of all necessary policies, and policies and procedures related to human resources.
As an undergraduate researcher, I worked at the Technological entrepreneurship Lab supervised by Doohee Chung for data analysis. As a data analyst, I participated in various projects related to Technological Entrepreneurship. In particular, I used a number of statistical techniques, including hierarchical regression, to analyze moderating effects, mediating effects, etc. through SPSS, STATA, and AMOS.
I worked as a general manager at an English camp for about 300 elementary and middle school students. I operated all the programs and other things related to the two-month camp schedule. From the camp preparation stage to the start and end of the camp, the whole process was in English.
I hosted an English class for about 100 elementary and middle school students at GVCS located in Sejong City, South Korea. Participated as an equivalent English instructor with 30 other native speakers. Also, I worked as an English interpreter for various events as well as conducted classes.
I participated in the orientation for 200 foreign freshmen as an accountant for a total of 6 semesters. I ran a budget of 30 million won each time and set up and implemented a program funding plan. Since most of the staff are also foreigners, we communicated in English from the preparation process to the end of the orientation.
Publications
Journal of Medical Internet Research, 2022
Journal of Technology Innovation, 2019 [PPT]
Korea Technology Innovation Society, 2019 [PPT]
Patents
Personal Studies
- [DL] Deep Learning Basic
- [DL] Multitask Learning
- [DL] Why does cross entropy use log function?
- [DL] Model inference using dropout
- [NLP] Preprocessing
- [NLP] Word Embedding
- [NLP] Named Entity Recognition
- [NLP] Bidirectional Encoder Representations from Transformers
- [NLP] Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- [NLP] Extractive Text Summarization
- [NLP] Topic Modeling
- [NLP] Langchain
- [Vision] Sora