Cheoneum Park

I am an assistant professor in the Department of Computer Engineering at Hanbat National University, where I focus on natural language processing (NLP). I also am the Director of NLP Lab, conducting research on superintelligence.

Hi! I'm NLP researcher who loves solving real-world challenges in both industry and academia. My focus areas include natural language processing, coreference resolution, question answering, dialogue systems, machine learning, and MLOps. I worked on a mobile agent at SK Telecom. At Hyundai Motor Company, I worked on a project to improve the question-answering abilities of our car agent and chatbot dialogue systems. Recently, I've had experience designing and deploying production models, as well as implementing cloud-based services.

CV  /  Google Scholar  /  Patents  /  LinkedIn

Selected Publications

[C]: conference [J]: journal [A]: arxiv [W]: workshop [D]: domestic

[23C] Spectral-Aligned Inference Guidance for Diffusion-based Image Super-Resolution

[22C] ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs

[21C] ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts

[20D] Introduction to Neural Retriever

[19C] SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors

[18J] MaQA: Car Manual Question Answering as a Neural FAQ Classification Problem

[17C] QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

[16J] ADMit: Improving NER in automotive domain with domain adversarial training and multi-task learning

[15J] Robust Multi-task Learning-based Korean POS Tagging to Overcome Word Spacing Errors

[14J] Multi-task learning with contextual hierarchical attention for Korean coreference resolution

[13W] Factual Error Correction for Abstractive Summaries Using Entity Retrieval

[12C] CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models

[11D] Introduction to Coreference Resolution

[10J] Korean TableQA: Structured Data Question Answering based on Span Prediction Style with S^3 -NET

[9C] Fast End-to-end Coreference Resolution for Korean

[8J] VS^3-NET: Neural Variational Inference for Machine Reading Comprehension

[7W] KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks on WAT 2019

[6W] ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples

[5J] S^2-NET Machine Reading Comprehension with SRUbased Self-matching Networks

[4J] Multitask Pointer Network for Korean Dependency Parsing

[3W] SEx BiST: A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations

[2W] KNU CI System at SemEval-2018 Task4: Character Identification by Solving Sequence-Labeling Problem

[1J] Anaphora Resolution with Pointer Networks

Design and source code from Jon Barron's website