[ ] update_state_user in dialogue_state_tracker.py
For more robust dialogue modeling, the following solution was proposed. It considers not only the most likely user intent, but a ranked list of predicted user intents.
user_intents = predict_user_intent(user_utterance, conv_history)
for user_intent in user_intents:
Check if user_intent can be executed
Do something
Break
Else
Sorry, I don’t understand
Some particularly problematic parts:
next_action
indialogue_policy.py
generate_dact
innlu.py
update_state_user
indialogue_state_tracker.py
For more robust dialogue modeling, the following solution was proposed. It considers not only the most likely user intent, but a ranked list of predicted user intents.