For each class, there is set of assigned readings. Each student is required to turn in a one page review on the assigned readings by 11:59 pm EST the night before the class. Late submissions will not be accepted.
Structure
Each review must include the following information:
- Summary: (An overview of the main idea and contributions in one paragraph.)
- What is this paper about?
- What is the main contribution?
- Describe the main approach & results. Just facts, no opinions yet.
- Summarize the insights resulting from the empirical study.
- Strengths: (State the strengths of the paper in three sentences.)
- Is there a new theoretical insight?
- Or a significant empirical advance? Did they solve a standing open problem?
- Or a good formulation for a new problem?
- Or a faster/better solution for an existing problem?
- Any good practical outcome (code, algorithm, etc)?
- Are the experiments well executed?
- Useful for the community in general?
- Weaknesses: (State the weaknesses of the paper in three sentences.)
- What can be done better?
- Any missing baselines? Missing datasets?
- Any odd design choices in the algorithm not explained well? Quality of writing?
- Is there sufficient novelty in what they propose? Minor variation of previous work?
- Why should anyone care? Is the problem interesting and significant?
- Reflections: (Present a question or comment on the paper in a paragraph.)
- What are the next research directions in this line of work?
- What (directly or indirectly related) new ideas did this paper give you? What would you be curious to try?
- What experiments can deepen our understanding?
- How does this relate to other papers we have read?
- How can your own research benefit from the insights provided in the paper?
- Why is the paper not interesting?
- What is the paper’s potential impact on the field?
You should strive for clarity and brevity in your reviews. You are encouraged to use active voice in your review. You should expect to spend around three hours per class on reading the paper and writing the review.
The presenter will discuss the questions and comments from their peers during the presentation. Students will be expected to actively participate in all class discussions including those on papers that they are not presenting. You need not submit paper reviews during the classes where you are leading discussions on the paper.
Students are allowed to miss reading review submissions for three classes during the semester.
Formatting Guidelines
We have provided a recommended latex template that you may want to use for your reviews. You can use other document processing tools while adhering to the same structure and formatting guidelines (12 point font, single spacing).
LaTeX Template: review.tex
PDF: review.pdf
Makefile: Makefile
Grading
Each review will be evaluated on a ten-point scale by the presenter.
- 8 points — Structure (summary [1], strengths [1], weaknesses [1], reflection [5]).
- 1 point — Prose (grammar, spelling, etc.).
- 1 points — Clarity (cogent arguments).
- 1 points — Bonus (exceptional reviews with innovative ideas).
The best review will be picked by the presenter.
Submission
Students will submit their review via email to the course email address and the presenter by 11:59 pm EST the night before the class. Late submissions will not be accepted. You should use the subject line "Review #X" where X represents the lecture number. You should send the review in the body of the email, not as an attachment.
The course email address is: gt.8803.ddl.fall.2018@gmail.com
Please hand in a printed copy of your review at the beginning of the class.
Reviewing Tips
I highly recommend reading the first article below.
- How to read a paper
- Notes on Constructive and Positive Reviewing
- The task of the referee
- How to write a review
LaTeX References
WARNING: These reading reviews must be your own writing. You may not copy from the papers or other sources that you find on the web. Plagiarism will not be tolerated. Students are expected to abide by the Georgia Tech Honor Code.