ExpressAI/omneval

Issues

• Suggestions & New Features

  #19 opened 3 years ago
  2

• can not run the example

  #18 opened 3 years ago
  1

• Leaderboard Design

  #17 opened 3 years ago
  0

• discussions

  #15 opened 3 years ago
  0

• add more evaluation perspectives in terms of models

  #14 opened 3 years ago
  2

• finish the outline of the overleaf

  #13 opened 3 years ago
  0

• benchmark dataset

  #12 opened 3 years ago
  1

• re-inplemented results

  #11 opened 3 years ago
  1

• evaluation metric for generation tasks

  #10 opened 3 years ago
  1

• prompting evaluation QA-Squad?

  #9 opened 3 years ago
  2

• this should be larger, which affect final performance

  #8 opened 3 years ago
  1

• add explaination of these input arguments

  #7 opened 3 years ago
  0

• add detailed comments

  #6 opened 3 years ago
  0

• add more comments (or even examples) for each task's prompting function

  #5 opened 3 years ago
  0

• support conll v.s brat format?

  #4 opened 3 years ago
  0

• not a span-based prompt?

  #3 opened 3 years ago
  0

• Can we draw a digram of our code base's framework?

  #2 opened 3 years ago
  1

• Can we add other sequence labeling tasks, like part-of-speech, chunking, cws, which would make our work stronger?

  #1 opened 3 years ago
  0