search

declare-lab / MELD

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation
GNU General Public License v3.0
788 stars 200 forks source link

Baseline results=0 #36

Open Aidenfaustine opened 3 years ago

Aidenfaustine commented 3 years ago

Hi, I have tried the bc_LSTM baseline with bimodal in emotion classification, but the F1-score and accuracy of 'fear' and 'disgust' are always zero, so I can't reproduce the result in paper.

The command I use:

python baseline.py -classify emotion -modality bimodal -train

The results:

      precision    recall  f1-score   support

   0     0.7322    0.7795    0.7551      1256
   1     0.4799    0.4662    0.4729       281
   2     0.0000    0.0000    0.0000        50
   3     0.2781    0.2019    0.2340       208
   4     0.4813    0.5448    0.5111       402
   5     0.0000    0.0000    0.0000        68
   6     0.3832    0.4377    0.4087       345

The emotion labels:

Emotion - {'neutral': 0, 'surprise': 1, 'fear': 2, 'sadness': 3, 'joy': 4, 'disgust': 5, 'anger': 6}.

I know the main strategy is to adjust the class weight. To be hnoest, I'm new to tensorflow. I don't know what codes are needed to add to achieve it. Could you please give me some suggestion?

Best wishes>