Email: [email protected] GitHub: soyoung97

Google Scholar: Soyoung Yoon Webpage: https://soyoung97.github.io/profile/

I am an incoming PhD student at Seoul National University, advised by Prof. Seungwon Hwang. I want to develop NLP systems that are beneficial and informative to people in everyday life. To achieve this, I am focusing on endowing language models with the ability to:

(1) efficiently stay up-to-date with new knowledge and human feedback,

(2) Incorporate internal (commonsense) knowledge with external knowledge,

(3) Generate reliable responses grounded on external knowledge base.

Education

Ph.D in Artificial Intelligence, Language & Data Intelligence Lab Integrated system of Artificial Intelligence, Seoul National University Research Interests: Generative Retrieval, Search Advisor: Prof. Seung-won Hwang

Sep 2023 - Present

M.S. in Artifical Intelligence, Language & Knowledge Lab Kim Jaechul Graduate School of AI, KAIST(Korea Advanced Institute of Science and Technology) Research Interests: Question Answering, Generative Retrieval, Semantic Parsing, NLP, ML Advisor: Prof. Minjoon Seo

GPA 4.1/4.3

B.S. in Computer Science (advanced major). Korea Advanced Institute of Science and Technology (KAIST). GPA 3.77/4.3 (Cum Laude). Major only: 3.92/4.3 ******

Mar 2021 - Aug 2023

Mar 2016 - Feb 2021

Publications

(5) ListT5: Listwise Reranking with Fusion-in-Decoder improves Zero-shot Retrieval. [paper]

Soyoung Yoon, Eunbi Choi, Jiyeon Kim, Hyeongu Yun, Yireun Kim, Seung-won Hwang

To be appeared in arXiv, 2024.

(4) An Integrated Search System for Korea Weather Data. [paper]

Jinkyung Jo, Dayeon Ki, Soyoung Yoon, and Minjoon Seo

In EMNLP Industry Track, 2023

(3) Continually Updating Generative Retrieval on Dynamic Corpora. [paper] ****

Soyoung Yoon*, Chaeeun Kim*, Hyunji Lee, Joel Jang, Sohee Yang, and Minjoon Seo In ****arXiv, 2023.

(2) Towards Standardizing Korean Grammatical Error Correction: Datasets and Evaluation. [paper] ****[code] Soyoung Yoon, Sungjoon Park, Gyuwan Kim, Junhee Cho, Kihyo Park, Gyu Tae Kim, Minjoon Seo and Alice Oh In Proceedings of ACL, 2023.

(1) SSMix: Saliency-Based Span Mixup for Text Classification. [paper] [code] [blog] Soyoung Yoon*, Gyuwan Kim*, Kyumin Park. In Findings of ACL, 2021. Also appeared on the 6th Workshop on Representation Learning for NLP(Rep4NLP), 2021

Research & Industry Experience

Seoul National University, Language & Data Intelligence Lab, PhD student

Advisor: Seung-won Hwang

LG AI, EXAONE Lab, Research Intern (3 months) Working on generative retrieval systems

KAIST Language* & *Knowledge Lab, M.S. student Advisor: Minjoon Seo. Working on generative retrieval systems

Hyundai AIRS, Research Intern (2 months) Worked on text-to-SQL semantic parsing. [preliminary report with results] Clova AI, Naver Corp, Research Intern (6 months) Advisor: Gyuwan Kim. Worked on the ACL 2021 Findings paper *KAIST U*&I Lab, Research Intern (8 months) Advisor: Alice Oh, Sungjoon Park. Worked on the Korean GEC paper, Awarded 3rd prize at URP workshop AI startup, Aitrics, SW developer Intern (8 months) Front & Back-end server engineer. Used Django-Rest Framework & Vue.js. Led to the talk at pycon

2023-

2023

2021~2023

2021~2022

2020~2021

2019-2020

2019

Honors and Awards

National Graduate Science & Technology Scholarship 3rd Prize, URP(Undergraduate Research Project) workshop [Slides] [Description] Title: Grammatical Autocorrection for Korean via Fine-tuning Pre-trained Language Models

2018-2021 2020

Invited Talks

Django Query Optimization for Real-time Medical AI data processing, Pycon Korea [Slides] [Video]

2019