macabdul9/CASA-Dialogue-Act-Classifier
PyTorch implementation of the paper "Dialogue Act Classification with Context-Aware Self-Attention" for dialogue act classification with a generic dataset class and PyTorch-Lightning trainer
PythonMIT
Issues
- 21
Does dataset class still have some problems?
#6 opened by nanzhao - 14
Prediction example?
#5 opened by glicerico - 0
What python version did you use?
#27 opened by poko1 - 3
Withdraw fake papers!
#22 opened by xiajinxiong - 0
Conversations / utterances
#25 opened by christinedekock11 - 0
Trained model available?
#26 opened by angoodkind - 3
What accuracy can you actually achieve?
#21 opened by xiajinxiong - 0
Pass callback instances to the `callbacks` argument in the Trainer constructor instead.
#20 opened by sbera7 - 1
Dataset
#19 opened by zhaoyuanyuan2011 - 0
Low Kaggle Accuracy
#18 opened by macksjeremy - 9
training seems to be too slow?
#7 opened by PolKul - 4
- 2
- 3
Restart from checkpoint not implemented
#13 opened by glicerico - 1
incompatible dataset labels
#10 opened by glicerico - 6
- 8
Training with unfreezed RoBERTa
#8 opened by macabdul9 - 2
Suspicious labels
#2 opened by glicerico - 1
Classifier ouputs `hidden_size` values
#3 opened by glicerico - 2
SwDA scores?
#1 opened by glicerico