Skip to content
View peinan's full-sized avatar
🏠
WFH
🏠
WFH
39 followers · 65 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: StarstruckAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: StarstruckAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Highlights

Block or report peinan

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
peinan/README.md

Hello, I'm Peinan.


I'm a Senior Research Scientist/Engineer/Manager at AI Lab, CyberAgent, Inc., Tokyo 🇯🇵

About me

📚   I'm specialized in natural language processing (NLP), especially natural language generation.
🔍   I also interested in language modeling, evaluation, and multimodality.
❤️   I love research, development and design.
💬   Ask me about anything here.

You can find my CV here.

Selected Publications

  • AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset [Paper] [Dataset]
    • Murakami Soichiro, Peinan Zhang, Hidetaka Kamigaito, Hiroya Takamura, and Manabu Okumura
    • In ACL 2025 Findings (To Appear)
  • AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising [Project Page] [Paper] [Dataset]
    • Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, and Taro Watanabe
    • In NAACL 2025
  • AdParaphrase: Paraphrase Dataset for Analyzing Linguistic Features toward Generating Attractive Ad Texts [Paper] [Dataset]
    • Soichiro Murakami, Peinan Zhang, Hidetaka Kamigaito, Hiroya Takamura, and Manabu Okumura
    • In NAACL 2025 Findings

See all publications here.

Skills

Languages

Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge

Frameworks

Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge

Tools

Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge Static Badge

Show some ❤️ by starring some of the repositories!


Pinned Loading

  1. CyberAgentAILab/AdTEC CyberAgentAILab/AdTEC Public

    The AdTEC dataset is designed to evaluate the quality of ad texts from multiple aspects, considering practical advertising operations.

    5 1

  2. CyberAgent/fast-annotation-tool CyberAgent/fast-annotation-tool Public

    FAST is an annotation tool that focuses on mobile devices. https://aclanthology.org/2021.emnlp-demo.41/

    TypeScript 53 7

  3. peinan.cc peinan.cc Public

    My portfolio and blog using Notion + TypeScript + Next.js + Vercel

    CSS

  4. swpy swpy Public

    A simple, yet useful stopwatch library

    Python 6

  5. iterm2-statusbar-components iterm2-statusbar-components Public

    Very cool iTerm2 status bar components that include 🌤weather information, 📀disk usage and so on.

    Python 17 2

  6. pdfchat pdfchat Public

    Gradio demo of LLM chatbot using RAGs

    Python 6 1