Skip to content
View philhoonoh's full-sized avatar

Highlights

  • Pro

Block or report philhoonoh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
philhoonoh/README.md

   GitHub followers    GitHub User's stars

Typing SVG

A passionate NLP engineer from South Korea 🇰🇷

About Me

GIF



🧐 Interests

I am currently a master's student at the Kim Jaechul Graduate School of AI, where I am fortunate to be advised by James Thorne. Before joining KAIST, I was a NLP engineer in SK Inc. C&C, and I received my bachelor's degree at UC Berkeley, majoring in Statistics.

I believe language plays a pivotal role in transferring knowledge. While humans appeared on Earth millions of years ago, civilization has only been built for thousands of years. It has only been in the last few hundred years that humans have made significant strides by accumulating knowledge through language. In other words, language enables people to think collectively beyond time and space. If we can expedite the sharing of knowledge by incorporating language into machines, it will be possible for humans to make further progress.

My primary interests lie in Information Retrieval (IR) and Question Answering (QA). I believe that every form of language (conversations, audio, text) can be reformulated as question + (external information) = answer format. This external information might include facial expressions, the speaker's tone, and contexts. With this perspective, I am particularly eager to delve deeper into areas described below:

  1. Information Retrieval

    • Information Retrieval encompasses a range of intriguing topics, such as Open-Domain Question Answering (ODQA), Multi-hop reasoning, and more.
    • Let's search for information that can help align with the user's intention.
  2. Fact Verification

    • Answering questions based on misleading information can have detrimental effects on society.
    • How can a model effectively discern facts from non-facts?
  3. Hallucination (Confabulation)

    • No definitive solutions have been found yet
    • Some potential remedies include prompting, ICL (In-Context Learning), and the utilization of external knowledge sources.
    • How might we effectively resolve this problem?

🛠  Tech Stack

Python  R  TensorFlow  PyTorch  FastAPI  Flask  MongoDB  MySQL  AWS  Google_Cloud 

Blog Post

Stats

Contacts

Pinned Loading

  1. Boostcamp-AI-Tech-Product-Serving Boostcamp-AI-Tech-Product-Serving Public

    Forked from zzsza/Boostcamp-AI-Tech-Product-Serving

    [Machine Learning Engineer Basic Guide] 부스트캠프 AI Tech - Product Serving 자료

    Python

  2. boostcamp_coding_test_study boostcamp_coding_test_study Public

    coding test study

    Jupyter Notebook

  3. final-project-level3-nlp-01 final-project-level3-nlp-01 Public

    Forked from boostcampaitech3/final-project-level3-nlp-01

    final-project-level3-nlp-01 created by GitHub Classroom

    Jupyter Notebook

  4. os os Public

    Operating System Study

    Jupyter Notebook

  5. spark spark Public

    spark study

    Jupyter Notebook

  6. transformers transformers Public

    Forked from huggingface/transformers

    🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

    Python