profile picture

Seanie Lee

Master Student

Education

M.S. in Artificial Intelligence

Korea Advanced Institute of Science and Technology
2020 - present

B.A. in Library and Information Science

Yonsei University
2011- 2018

Languages

  • Korean (Native)
  • English (Intermediate)

Interests

  • Natural Language Processing
  • Machine Learning
  • Mathematics
  • Statistics

Career Profile

I am master student at KAIST, working on natural language processing and machine learning. My supervisor is Sung Ju Hwang. Previously, I was research intern at 42Maru. Here is my CV.

Publications

  • Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
    • Seanie Lee*, Dong Bok Lee*, Sung Ju Hwang
    ICLR 2021
  • Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning
    • Dong Bok Lee, Dongchan Min, Seanie Lee, Sung Ju Hwang
    ICLR 2021
  • Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
    • Dong Bok Lee*, Seanie Lee*, WooTae Jeong, Donghwan Kim, Sung Ju Hwang
    ACL 2020
  • g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset
    • Kyubyong Park*, Seanie Lee*
    INTERSPEECH 2020
  • Domain-agnostic Question-Answering with Adversarial Training
    • Seanie Lee*, Donggyu Kim*, Jangwon Park*.
    EMNLP-IJCNLP 2019 MRQA Workshop shared task
  • Incorporating product description to sentiment topic models for improved aspect-based sentiment analysis
    • Reinald Kim Amplayo, Seanie Lee, and Min Song.
    Information Sciences 454 (2018): 200-215

    Experiences

    Research Intern

    2019.2 - 2020.1
    42Maru, Seoul
    • Research on question generation and semi-supervised learning
    • Domain adaptation for Question Answering

    Projects

    Group study of Mathematical Statistics - Group Study of mathematical statistics. The main text book is mathematical statistics by 김우철
    Benchmark dataset and package for Chinese Grapheme to Phoneme - Release a new open-source benchmark dataset for Chinese Grapheme to Phoneme and python package
    Pytorch implementation for Question Generation - Pytorch implementation for the paper Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks.
    Group study of Linear Algebra - Group Study of Linear Algebra. The main text book is Elementary Linear Algebra (Friedberg et al) and 선형대수와 군 (Linear Algebra and Group)
    Silver Medal in NLP challenge - Won silver and bronze medal in NER (Named Entity Recognition) and SRL (Semantic Role Labeling).

    Skills & Proficiency

    Natual Language Processing

    Deep Learning

    Mathematics

    Statistics