google / google/example_extrapolation
Did you use clinc150 data_imbalanced vs data_full?
Aperta
- Lingua principale
- Python
- Stelle
- 9
- Fork
- 4
- Metriche di merge delle PR
- Nessuna PR unita negli ultimi 30g
Descrizione
Hi,
I experimented with verifying your approach however I didn't receive such low F1 numbers for few shot. In looking at data_full, banking has the same amount of training samples as all other domains/intents. Did you in fact use data imbalanced?
Guida per i contributori
Apri la guida per i contributori
Valutazione
Questa issue non è ancora stata valutata.