Name: yukyunglee
Type: User
Company: Korea University DSBA Lab.
Bio: Ph.D. Candidate @ Korea University | Former Research Intern @ Naver |
Interests: Writing with AI, Evaluation, Conversational AI, Anomaly Detection
Location: Seoul,Korea
Blog: yukyunglee.github.io
yukyunglee's Projects
The 2019 Competition problem will ask student teams to look into the future, helping GM analyze how autonomous vehicles may change the finished vehicle and delivery operation process. The problem involves designing a vehicle delivery network, including the routing for each plant-dealer-vehicle combination. The objective is to minimize total costs while satisfying all constraints. Students will be provided with GM datasets, as well as a description of key assumptions, defined output formats for the report, clear evaluation criteria, and references.
Dialogue State Tracking (DST) Papers, Datasets, Resources π€©
GoldenPass νμ μΉ΄μΉ΄μ€ μλ λ "λΈλ°μΉ μ¬μ©μλ₯Ό μν κΈ μΆμ² λν"μ μ΅μ’
μ μΆ μ½λμ
λλ€.
Deeplearningbook(Ian Goodfellow) group study in DSBA
ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624
End-to-End Object Detection with Transformers paper, code review (KoreaUniv. AAA739)
Various dst model re-implementation codes, resources, etc.
μ€ν°λ κ·Έλ£Ή GoldenPassμμ 곡λΆνλ λ΄μ©μ μ 리ν΄λλ repo.
BERTScore for Korean
μ΄μμΉ νμ§ μ μ²λ¦¬ λͺ¨λ
LG μλμ§μ루μ
CNN Part 2 μ€μ΅μλ£
LG μλμ§μ루μ
Transformer μ€μ΅μλ£ (TransformerκΈ°λ° μ΄μμΉ νμ§)
Practice and tutorial-style notebooks covering wide variety of machine learning techniques
Multi^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (Findings of ACL: EMNLP 2020)
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Jiphyeonjeon Season 2
SOM-DST: Efficient Dialogue State Tracking by Selectively Overwriting Memory (ACL 2020)
Modified version of T5-DST for Dialogue State Tracking.
"A survey of Transformer" paper study π©π»βπ»π§π»βπ» KoreaUniv. DSBA Lab
huggingface transformers tutorial, code, resources
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities