Shannon Zejiang Shen

I am a first year PhD Student at MIT CSAIL,
working at the intersection between NLP and HCI.


On the NLP side, I am interested in language understanding in scientific, legal, or clinical text, documents that are typically authored and used by domain experts.

On the HCI side, I explore how humans, especially domain experts, and AI models, e.g., Large Language Models, can communicate and collaborate.

I also developed a suite of tools for document understanding and parsing. Please check my projects on Document Intelligence for more information.



Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks New

Zejiang Shen, Tal August, Pao Siangliulue, Kyle Lo, Jonathan Bragg, Jeff Hammerbacher, Doug Downey, Joseph Chee Chang, and David Sontag


Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities Featured

Zejiang Shen, Kyle Lo, Lauren Yu, Nathan Dahlberg, Margo Schlanger, and Doug Downey

NeurIPS 2022 Datasets and Benchmarks Track


Generating Object Stamps

Youssef Alami Mejjati, Zejiang Shen, Michael Snower,
Aaron Gokaslan, Oliver Wang, James Tompkin, and Kwang In Kim


Deep Learning based Framework for Automatic Damage Detection in Aircraft Engine Borescope Inspection

Zejiang Shen, Xili Wan, Feng Ye, Xinjie Guan, and Shuwen Liu

2019 International Conference on Computing, Networking and Communications (ICNC)


Besides research, I've worked on various open source projects and here are a few of them:

Websites & Design

A platform for current and past grad students to share their statement of purposes during application to help future applicants. It is a full-fledged website based on notion, and we develop an automated submission system that connects the notion database with a google form (code available here).

The layout-parser project website is built based on jekyll and bulma. Most interestingly, the layout-parser platform subpage is rendered by live fetching the model metadata stored in Github issues.

Avalanche: a personal website theme for academics

Also based on jekyll and bulma, the Avalanche theme can be used out-of-the box for creating an academic site beautifully displaying personal research description, publications, as well as recent news.

Productivity & Utils


A python package that seamlessly connects notion databases and pandas dataframe. It allows for easy uploading/downloading notion databases to/from pandas dataframe.


Whenever you have any questions regarding my research (or just want to say hi), the best email address to find me is zejiangshen^