j-hartmann
/
emotion-english-distilroberta-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Hartmann 2022-03-28 06:06:39 +00:00 committed by huggingface-web
parent 5e453b0f6c
commit adfea0d846
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -93,6 +93,6 @@ Please find an overview of the datasets used for training below. All datasets co
|GoEmotions, Demszky et al. (2020)|Yes|Yes|Yes|Yes|Yes|Yes|Yes| |GoEmotions, Demszky et al. (2020)|Yes|Yes|Yes|Yes|Yes|Yes|Yes|
|ISEAR, Vikash (2018)|Yes|Yes|Yes|Yes|-|Yes|-| |ISEAR, Vikash (2018)|Yes|Yes|Yes|Yes|-|Yes|-|
|MELD, Poria et al. (2019)|Yes|Yes|Yes|Yes|Yes|Yes|Yes| |MELD, Poria et al. (2019)|Yes|Yes|Yes|Yes|Yes|Yes|Yes|
|SemEval-2018, EI-reg (Mohammad et al. 2018) |Yes|-|Yes|Yes|-|Yes|-| |SemEval-2018, EI-reg, Mohammad et al. (2018) |Yes|-|Yes|Yes|-|Yes|-|
The model is trained on a balanced subset from the datasets listed above (2,811 observations per emotion, i.e., nearly 20k observations in total). 80% of this balanced subset is used for training and 20% for evaluation. The evaluation accuracy is 66% (vs. the random-chance baseline of 1/7 = 14%). The model is trained on a balanced subset from the datasets listed above (2,811 observations per emotion, i.e., nearly 20k observations in total). 80% of this balanced subset is used for training and 20% for evaluation. The evaluation accuracy is 66% (vs. the random-chance baseline of 1/7 = 14%).