Schedule

1/24 - Course Overview & Research Method Strategies and Best Practices [Slides -- pdf, key]
1/31 - "Success Story" Presentations from last semester [Slides]
2/7 - Project proposal presentations (Group 1)
2/14 - Project proposal presentations (Group 2)
2/21 - Special office hours with instructors
2/28 - Senior career path stories (2 local + 2 remote)
3/6 - Reserved for guest lecture by Prof. Michelle Trim (Ethics in data Science) [slides]
~~3/12- Evening Hackathon (6:00pm - 8:30 pm in CS150)~~
3/13 - Friday before recess
3/20 - No Class - Spring Vacation
3/27 - Midpoint presentations (Group 1)
4/3 - Midpoint presentations (Group 2)
4/09- Evening Hackathon (6:00pm - 8:30 pm in CS150)
4/10 - Career Panel
4/17 - Extended TA hours
4/24 - Teams in Group 1 give project final presentations
5/1 - Teams in Group 2 give project final presentations
5/6 - Last day of exams - Due: Teams had in final project report by 5p.m.
Before the end of the year: peer feedback review.

Schedule is Tentative and Subject to Change

Project Proposal Instructions

Follow the same guidelines (presented below) for both the presentation and the report.
We will be very strict w.r.t the timing of your presentation slides. Its going to be 10 mins (with 7 mins of presentation + 3 minutes of QA). Once again, since there are 11 teams presenting in a class, we will not tolerate going overtime. Please practice your presentation. Also here is a link to a demo proposal presentation that Lorraine did that you could use as a reference.
Report due 3/9 (Monday) (5 PM ET by email to rajarshi at cs dot umass dot edu). Report template: Link

Please include the following in your project proposal:

Title for your project (this can also change later on). Something descriptive but also memorable.
Introduction section which must contain the following subsections:
- Task / Research Question Description: What is the task you are trying to solve or what is the research question you are trying to answer?
- Motivation & Limitations of existing work: Have others tried to solve the same task or answer a similar research question? What are you trying to do differently and why? What were the limitations or shortcomings of prior work?
- Proposed Approach: Briefly describe some of your initial thoughts about your proposed approach and your preliminary ideas
- Likely challenges and mitigations: What is hard about this task / research question? What are your contingency plans if things turn out to be harder than expected or experiments do not go as planned?
Related Work Section
- Include 2-3 sentence descriptions of no less than 4 relevant papers. Also mention how your work differs from these.
Experiments section
- Datasets - Please list which datasets you plan to use , whether or not you have access them, and whether or not they are publicly available with the same preprocessing and train / dev / tests as the previous work you will be comparing to (if applicable).
- Baselines - Please list the baseline methods (if applicable) that you will compare to, importantly state whether or not you will need to run their method on new datasets or if you have already published results. Also list if they have publicly available source code that can be used to run experiments.
- Software - Please list some of the software libraries / components / existing code that you will be building your project off of.
- Timeline - Please provide a week-by -week timeline for the next few weeks leading up to the midpoint presentations on 10/18. What experiments will you do each week? What would you like to have accomplished by the midterm? How will you implement an end-to-end If you're in a team how will you divide up the work?
- Challenges: Lay down the challenges that you can foresee which might prevent you from attaining your goal.
- Contingency Plan: Set of backup experiments / model that you would try out in case if the original plan does not work out.

Project Teams

Group 1: Amazon 1, CZI 3, GE1, Goldman Sachs, IBM 1, IBM 2, Microsoft 3, Microsoft 4, Stanley Black & Decker,Oracle Labs

Group 2: GE2, Amazon 2, Amazon 3, CZI 1, CZI 2, Lexalytics, Microsoft 1, Microsoft 2, Raytheon, UMass, Voya and Lexalytics, FAIR

----------------------------------------------------------

Microsoft 1: Responsible AI

Xinlu Li, Abdul Hannan Kanji, Ge Gao, Parul Gupta

Microsoft 2: Interpretable, tree-based reasoning

Apurva Bhandari, Shezan Rohinton Mirzan, Pulkit Sharma

Microsoft 3: Human-agent, co-operative reinforcement learning

Abhik Singla, Aarshee, Mishra, William Goss, Nicholas Perello

Microsoft 4: Neural Ranking Models with Transformers

Praful Johari, Karnika Agarwal, Sai Sumanth Palakurthy, Shubhankar Ajit Kothari

GE Precision Healthcare LLC 1: Development of AI Techniques to Enable ‘Mindshare’ Analysis of Published Medical Literature

Apurva Swarnakar, Kartik Mittal, Rishabh Agrawal

GE Precision Healthcare LLC 2: Development of Computer Vision Applications Using X-ray Medical Images to Enhance Quality, Workflow, and Patient Care

Ho Yin Au, Nikhil Maryala, Surya Deekshith Gupta Mudiyanur, Ankita Naik

Raytheon: Digital Transformation and Social Media

Ye Zhang, Pavan Reddy Bommana, Chaitanya Varma

Voya and Lexalytics: Ranking stocks using SEC filings of companies

Deepanshu Pariyani, Kajal Tiwari, Nikita Agarwal

Lexalytics: De-biasing Contextualized Word Representations

Prashant Ranjan, Hoang Ho, Krishnkant Swarnkar

UMass: Pompeii Artistic Landscape Project

TBD, TBD, TBD

Stanley Black & Decker: Competitive Market Intelligence

Saurabh Shirodkar, Arvind Govindarajan, Yuchen Cai

Facebook Artificial Intelligence Research (FAIR): Dialogue Coherence

Daivik Swarup, Aditya Vikram Agarwal, Ritu Yadav

Amazon Alexa 1: Commonsense reasoning given a pair of sentences and generating explanations

Sanchit Nevgi, Anupam Yadav, Sumeha Kashyap, Sangeetha Balasubramanian

Amazon Alexa 2: Methods for Sparsification of Word Embeddings

Wenlong Zhao, Saurabh Kumar Shashidhar, Prafull Prakash

Amazon Alexa 3: Conversational Reasoning using KGs

Abhishek Ahuja, Shruti Chanumolu, Raghuveer Thirukovalluru

Goldman Sachs: Preserving critical facts in abstractive summarization

Pradhiksha Ashok Kumar, Sai Pavitra Dangati, Ahsaas Bajaj

IBM Research 1: Evaluating Natural Language Inference Models for Question Answering

Aparna Vijayakumar, Dhruvesh Patel, Anshuman Mishra

IBM Research 2: Using Graph Neural Networks for Drug-Drug Interaction Detection

Arthur Feeney, Yash Adhikari, Gayathri Venu Madhuri Chandu, Rishabh Gupta

CZI 1: To prove or disprove the role of preprint servers in the formation of new ideas.

Swarup Satish, Zonghai Yao

CZI 2: Studies of Citation Sentences and Claims in the Rare Disease Literature

Purujit Goyal, Kathryn Ricci, Anjali Ramaprasad, Kaivankumar Shah

CZI 3: Biomedical QA system

Karthick Gunasekaran, Vaishnavi Kommaraju, Kun Li

Oracle Labs, Machine Learning Research Group: Fairness for Ranking Models in Machine Learning

Ananya Gupta, Aditya Kumar Roy, Eric Johnson

Report abuse