Milestones

Milestone 2 :

Text processing and structure. The team will apply text processing techniques to build model-ready data for the answer and sentence level of each response. Specifically, the text will be transformed into part-of-speech tags (e.g., noun, verb, prep., etc.) as well as processed by public AI language models. 

Milestone 1 :

Text collection and preparation. The team is provided with sample data to follow and collect our own datasets. More specifically, the team will build a text dataset in the format {question, human_answer}. Then, for each question, the team will generate responses from ChatGPT (at least two responses). Finally, the team will apply AI-paraphrasing technologies to generate different versions of the responses. Several products will be delivered such as: PowerPoint presentation/video, updated Gannt chart, research paper draft, updated website, and weekly report updates. Please see the documentation page to view these files.