Soyoung Yang

I am a PhD student at KAIST AI advised by Jaegul Choo.

My research interests lie in natural language processing (NLP), especially for large language models (LLMs) and information extraction (IE) that aims to extract structured information from unstructured text. I also interested in diverse applications in NLP and computer vision.

Before joining KAIST, I completed my Bachelor's degree at Korea University, majoring in Sinographic Literatures and Language, Brain & Computer as a relational major.

Email / Google Scholar / Linked-In / Github / CV

News

03.2024-Current. I've been honor to be a co-lab leader of DAVIAN Lab.
07-10.2023. I joined NLP team in SAIT as a research intern, mentored by Wonik Cho.

Publications

LLM ABSA Information Extraction
Single Ground Truth Is Not Enough: Adding Flexibility to Aspect-Based Sentiment Analysis Evaluation
Soyoung Yang, Hojun Cho, Jiyoung Lee, Sohee Yoon, Edward Choi, Jaegul Choo, Won Ik Cho
NAACL 2025.
Paper

LLM
Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information
Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo
Preprint.
Paper

ABSA Information Extraction
Evaluating Span Extraction in Generative Paradigm: A Reflection on Aspect-Based Sentiment Analysis
Soyoung Yang, Won Ik Cho
ArXiv Preprint.
Paper

Relation Extraction Historical Records Information Extraction
HistRED: A Historical Document-Level Relation Extraction Dataset
Soyoung Yang, Minseok Choi, Youngwoo Cho, Jaegul Choo
ACL 2023.
Paper / Github / HuggingFace

Selected for the KAIST `Kim Jae-Cheol AI Development Fund' AI Dataset Challenge project and received a research grant of KRW 50 million to conduct KAIST's own research project.

Event extraction Information Extraction
AniEE: A Dataset of Animal Experimental Literature for Event Extraction
Dohee Kim*, Ra Yoo*, Soyoung Yang, Hee Yang, Jaegul Choo
EMNLP 2023 Findings.
Paper

NMT
Towards Formality-Aware Neural Machine Translation by Leveraging Context Information
Dohee Kim*, Yujin Baek*, Soyoung Yang, Jaegul Choo
EMNLP 2023 Findings, Short paper.
Paper

NMT
Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning
Cheonbok Park*, Yunwon Tae*, TaeHee Kim, Soyoung Yang, Mohammad Azam Khan, Lucy Park, Jaegul Choo
ACL 2021.
Paper

Historical Records NMT
Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation
Kyeongpil Kang, Kyohoon Jin, Soyoung Yang, Sujin Jang, Jaegul Choo, Youngbin Kim
NAACL 2021.
Paper

Computer Vision
Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
Youngin Cho*, Junsoo Lee*, Soyoung Yang, Juntae Kim, Yeojeong Park, Haneol Lee, Mohammad Azam Khan, Daesik Kim, Jaegul Choo
WACV 2023.
Paper

Computer Vision
CG-NeRF: Conditional Generative Neural Radiance Fields for 3D-aware Image Synthesis
Kyungmin Jo*, GyuMin Shim*, Sanghun Jung, Soyoung Yang, Jaegul Choo
WACV 2023.
Paper

Computer Vision Visualization
VATUN: Visual Analytics for Testing and Understanding Convolutional Neural Networks
Cheonbok Park*, Soyoung Yang*, Inyoup Na*, Sunghyo Chung, Sungbok Shin, Bum Chul Kwon, Deokgun Park, Jaegul Choo
EuroVis 2021, Short paper.
Paper

Visualization
AILA: Attentive interactive labeling assistant for document classification through attention-based deep neural networks
Minsuk Choi, Cheonbok Park, Soyoung Yang, Yonggyu Kim, Jaegul Choo, Sungsoo Ray Hong
CHI 2019.
Paper / Video

Other activities

Reviewing activities

Serving as a reviewer for ARR'24.

Template based on Jon Barron's website.