Reading Papers

Revision as of 16:08, 22 January 2021 by David (talk | contribs)
\( \newcommand{\P}[]{\unicode{xB6}} \newcommand{\AA}[]{\unicode{x212B}} \newcommand{\empty}[]{\emptyset} \newcommand{\O}[]{\emptyset} \newcommand{\Alpha}[]{Α} \newcommand{\Beta}[]{Β} \newcommand{\Epsilon}[]{Ε} \newcommand{\Iota}[]{Ι} \newcommand{\Kappa}[]{Κ} \newcommand{\Rho}[]{Ρ} \newcommand{\Tau}[]{Τ} \newcommand{\Zeta}[]{Ζ} \newcommand{\Mu}[]{\unicode{x039C}} \newcommand{\Chi}[]{Χ} \newcommand{\Eta}[]{\unicode{x0397}} \newcommand{\Nu}[]{\unicode{x039D}} \newcommand{\Omicron}[]{\unicode{x039F}} \DeclareMathOperator{\sgn}{sgn} \def\oiint{\mathop{\vcenter{\mathchoice{\huge\unicode{x222F}\,}{\unicode{x222F}}{\unicode{x222F}}{\unicode{x222F}}}\,}\nolimits} \def\oiiint{\mathop{\vcenter{\mathchoice{\huge\unicode{x2230}\,}{\unicode{x2230}}{\unicode{x2230}}{\unicode{x2230}}}\,}\nolimits} \)

Things to look for when reading papers.

How I read papers

I'm not very experienced but here is how I read papers:

  • Watch their video.
    • Their video will give a high-level summary. Usually video explanations are faster/easier to understand.
    • Sometimes they show their results. Pay attention to problems in their results.
    • If they don't have a video, look for a third-party one on YouTube.
  • Read the abstract.
  • Look through all figures and captions.
  • Read the Intro and Methods.
    • Tells you the problem they're addressing and their approach to addressing it.
    • What is the input to and output of their pipeline?
  • Read the Related Works section.
    • This gives you an idea of what others have tried.
  • Read the Evaluation section.
    • Usually this is just a bunch of tables and numbers but it can give you links to datasets and a reference for some benchmarks.

Resources