Dian Chen is a seasoned senior algorithm engineer with about a decade of AI/ML experience, based in Haidian District, Beijing. He currently leads cognitive and interactive recommendation initiatives at Alibaba's Taotian search and push platform, delivering projects from proposal to production. His track record includes building and evolving RecGPT, DoR, and interactive recommendation systems, with measurable improvements in discovery metrics and new team formation. An active open-source contributor, he focuses on NLP and text correction, notably contributing to pycorrector where he improved inference and handling of UNK tokens and out-of-vocabulary words. Dian holds a PhD in data mining and machine learning from the University of Chinese Academy of Sciences and a bachelor's in IoT from Chongqing University. He blends research rigor with practical, scalable delivery across AI, NLP, and recommender systems, underpinned by hands-on experience across finance, tech, and enterprise platforms.
pycorrector is a toolkit for text error correction. 文本纠错,实现了Kenlm,T5,MacBERT,ChatGLM3,Qwen2.5等模型应用在纠错场景,开箱即用。
Role in this project:
ML Engineer
Contributions:2 reviews, 14 commits, 1 PR in 3 days
Contributions summary:Dian's commits focus on improving the text error correction model within the pycorrector repository. They addressed misalignment issues with UNK tokens, handled spaces and out-of-vocabulary words, and considered different scenarios during prediction. They primarily modified the `infer.py` file, which suggests they are working on the inference process and model behavior.
Contributions:25 commits, 23 pushes in 1 year 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.