Reading Papers: Difference between revisions

From David's Wiki
 
(One intermediate revision by the same user not shown)
Line 10: Line 10:
* Read the abstract.
* Read the abstract.
* Look through all figures and captions.
* Look through all figures and captions.
** If it doesn't have pictures, it's probably too theoretical so discard it. 😃
* Read the Intro and Methods.
* Read the Intro and Methods.
** Tells you the problem they're addressing and their approach to addressing it.
** Tells you the problem they're addressing and their approach to addressing it.
** What is the input to and output of their pipeline?
** What is the input to and output of their pipeline?
* Read the Related Works section.
* Read the Related Works section.
** This gives you an idea of what others have tried.
** This gives you an idea of what others have tried. Especially important if you don't work in the field.
* Read the Evaluation section.
* 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.
** Usually this is just a bunch of tables and numbers but it can give you links to datasets and a reference for some benchmarks.
** This is important if you plan on building upon the work.


==Resources==
==Resources==
* [https://www.youtube.com/watch?v=Uumd2zOOz60 Yannic Kilcher How I Read a Paper]
* [https://www.youtube.com/watch?v=Uumd2zOOz60 Yannic Kilcher How I Read a Paper]

Latest revision as of 19:34, 22 September 2022

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. Especially important if you don't work in the field.
  • 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.
    • This is important if you plan on building upon the work.

Resources