Code Monkey home page Code Monkey logo

Jinu Lee


Research Interests

To the grand goal of explainable and intelligent systems, I am currently interested in integrating deep language AI with symbolic systems, knowledge representation, and reinforcement learning.

Current research interests:

  • Explainable / Interpretable NLP training and inference
  • NLP with symbolic systems (Logic, Compiler, Knowledge base, …)
  • Language models as Reinforcement Learning agents

Career

👨‍⚖️ 07.2023 - 05.2024 Research Engineer, LBox (Legal Tech Startup)

🏫 09.2022 - 07.2023 Research Intern, SNU Language & Data Intelligence Lab (Adviser: Prof. Seungwon Hwang)

🚢 03.2021 - 09.2022 Researcher Seaman, RoK Navy Future Innovation Research Group

🎮 07.2020 - 11.2020 Research Intern, NCSOFT Language AI Lab


Education

💻 03.2018 - 08.2024 Dept. of Computer Science & Engineering, Seoul National University (Major)

📝 09.2019 - 08.2024 Dept. of Linguistics, Seoul National University (Minor)


More Information in...

🌱 Jinu Lee Profiles


Contact

✉️ [email protected]

Jinu Lee's Projects

bert_diora icon bert_diora

Implementation of DIORA(Deep Inside-Outside Recursive Autoencoder) with pretrained transformer embeddings.

birdman icon birdman

:bird: Birdman is a powerful package for asynchronous streaming of any web content. Ignorantly watch over like a bird, and we will bring you the whole world. That is the virtue of unexpected ignorance.

brio icon brio

ACL 2022: BRIO: Bringing Order to Abstractive Summarization

cont icon cont

[NeurIPS'22] CoNT: Contrastive Neural Text Generation

crawling icon crawling

Various corpus crawling/filtering scripts.

cutoff icon cutoff

The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation".

diora icon diora

Deep Inside-Outside Recursive Autoencoder

kmdp icon kmdp

Korean Morpheme-based Dependency Parsing framework(rule-based).

kogpt2-autoqag icon kogpt2-autoqag

Korean Auto Question-Answer Generation using fine-tuned KoGPT-2(by SKTBrain)

korcorr icon korcorr

KorCorr: Korean Spelling Auto-correction with Seqence-labeling based copy generation

scasp icon scasp

s(CASP), but with original Negation as Failure(NAF)

victornlp_dp icon victornlp_dp

Dependency parsing library that supports various models and languages

victornlp_re icon victornlp_re

Relation Extraction library that supports various models and languages

victornlp_sts icon victornlp_sts

Semantic Text Similarity(STS) library that supports various models and languages

xclingo2 icon xclingo2

A tool for explainability and debugging in Answer Set Programming.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.