Link Search Menu Expand Document
Data-Centric NLP (USC CSCI-699)

Assignments and Grading

There will be three components to course grades:

Paper Discussion (20%)

Students will be expected to present two research papers by leading class discussion on these papers. Each paper presentation is responsible for 10% of the total grade. The papers themselves will be selected by the instructor, but students can sign up their names 1-2 different papers; after the first two weeks the instructor will assign you to a paper which you might be presenting with another student. The presentation format should ideally involve slide decks designed to help everyone in the class understand the papers — think of yourself as the author of the paper presenting it at a conference venue. The purpose of this presentation is not only to discuss the findings of the paper, but to connect the paper with other papers and lectures visited before. The presenter is also encouraged to prepare 2-3 discussion questions to encourage discussion after the presentation.

Important Note about Academic Policy

For many of the assigned readings, the authors’ own slides and even video are publicly available. While students may watch these videos, they must make their own slides, and draw their own conclusions, as this discussion is intended to be the students’ own work. If you must borrow a slide or two from elsewhere, attribute the source on each individual slide. Non-adherence might amount to plagiarism, which amounts to a serious academic misconduct. If you find the paper assigned to you too difficult to follow, please let the instructor know and your request will be considered.

Class participation (20%)

Students are expected to participate in class discussions by not only asking questions, but also sharing their opinions on the topics under discussion. Students are also expected to turn in quiz sheets filled based on small group discussions. Note that quiz sheets will be distributed in some, but not all of the classes. Quiz sheets are due by 11:59 PM PT on the day of the class.

Class project (60% total)

Students must individually or in teams of two (at maximum) complete a final research project on a topic related to the class. This project is expected to include novel research on either (1) building analytical tools for investigating large-scale datasets, or (2) replicating tools from prior research to apply on new datasets. Please come to office hours or email me if you have questions related to choosing a project direction.

Project proposal (10%).

Students should submit a ~2-page proposal for their project by the end of Week 5 (Sep 21). The proposal should :

  • state and motivate the problem,
  • situate the problem within related work,
  • state a hypothesis to be verified, and
  • a brief description of the approach to be followed to verify the hypothesis.

Project progress report (10%).

Students should submit a ~5-page progress report for their project by the end of Week 10 (Oct 28). This report should:

  • once again describe the project’s goals (it is okay if this has changed since the proposal),
  • contain initial result, and
  • must outline a concrete plan of what will be done for the final report.

While the initial results might be inconclusive, you are expected to have made non-trivial progress by this point. The project proposal may be repurposed for this report (however, do NOT delete your project proposal pdf in your shared folder). Please take into consideration the earlier feedback you received, and address those inline (you may highlight these in a different text color if you wish to draw the instructor’s attention).

Project final presentation (10%).

This will be a 15 minute presentation, followed by 2 minutes of Q/A during the last two / three weeks of class. Points will be deducted if 15+2 min time limit is exceeded, so please practice with timing your talk. If in teams of two, each student must present an equal share of the work. Each project presentation should describe

  • the research questions to be answered and the underlying motivation,
  • the proposed methods, and
  • their findings so far, as well as
  • address audience questions.

Bonus points will be awarded to students who attend the final presentations when they are not presenting. If you have used up late days, you can gain 2 late days if you attend all three presentations that are not your own (if you miss any, you will not gain any late days). If you haven’t used up late days, you will be awarded bonus points for class participation.

Project final report (30%).

Students should submit a ~8-page final report detailing all aspects of their project. The report should be structured like a conference paper, including an abstract, introduction, related work, and experiments; a tech report format is discouraged. Parts of the proposal and progress report may be reused for the final report. Negative results will not be penalized, but should be accompanied with detailed analysis of why the proposed method did not work as anticipated.

All written assignments related to the final project should use the standard *ACL paper submission template.

Late Days

Students are allowed a maximum of 4 late days total for all assignments (not quiz sheets).