Project Description
The goal of this research is to leverage automatic question-answer generation to develop an integrated system where teachers can collaborate with AI to create and customize interactive reading resources with question-answering functions for their students from kindergarten through second grade. Throughout this project, students will have a chance to 1) develop innovative AI models that expand the state-of-the-art NLP techniques (e.g., BERT, GPT) for automatically generating question-answer pairs for reading materials and customizing the training to meet the unique requirements of an educational context; and 2) building a dialog system with graphical user interfaces that is able to a) ask children a question, b) provide tailored feedback and explanation to children’s response, and/or c) rephrase the original question (usually open-ended) to a multiple-choice question as a way of scaffolding if the children do not answer the original question or answer it incorrectly.
Team Members
- Liliana Nguyen
- Hugo Lin
- Wesley Truong
- Edwin Yee
- Shamita Gurusu
Professor and Mentors
- Prof. Shiyu Chang
- Grad mentor: Yujian Liu and Jiabao Ji
Meeting Time
- Meeting with the Professor
- TBD
- Meeting with Grad mentor
- TBD
- ERSP meeting with central mentors
- Chinmay: TBD
- Diba: TBD
- ERSP team meeting
- Fridays 5-7p
Links to Proposals and Presentation
- Instructor feedback on initial draft of proposal: link
- Final Proposal (after instructor's feedback): link
- Final presentation: link
Individual Logs
Peer Review
Project Documentation and Resource
- Andrew Ng -- Courera course playlist: https://www.youtube.com/watch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN