Project Description

The project will be developing an information retrieval system in C++ and Python.

The main tasks planned are:

  1. Learning basic information retrieval techniques on document indexing, retrieval and ranking.
  2. Reading a few information retrieval papers with machine learning. 
  3. Most of the students’ time will be spent on studying 2 or more open source search packages, reading their code, and integrating them with some extensions.

We may change the above planning based on the project progress.

The project can take on 3 students.

Prerequisite Information

None

Knowledge/Skills to Acquire (with guidance from mentors)

  • Extensive programming with self-learning will be involved.
  • C++ (arrays/classes/file operations). Python (PyTorch), Linux programming environment 
  • Data structures: Lists/ trees/graphs
  • Math concepts:  Vector/matrix  operations and their relationship to graphs (needed for programming)
  • Partial derivatives for multi-variable functions (useful concepts to know/learn when reading the research papers)

Team Members

  • Palvi Sabherwal
  • Leyang Ni
  • Dalia Sebat
  • Mitali Gaidhani

Professor and Mentors

  • Prof. Tao Yang
  • Grad mentor:  Parker Carlson

Meeting Times

  • Mentor Meetings
    • Fridays, 11 a.m. (biweekly)
  • ERSP Team Meetings
    • Mondays, 5-6 p.m.
    • Tuesdays, 5-6 p.m.

Research Logs