Settings related to NLU.
JSON representation |
---|
{ "modelType": enum ( |
Fields | |
---|---|
model |
Indicates the type of NLU model. |
classification |
To filter out false positive results and still get variety in matched natural language inputs for your agent, you can tune the machine learning classification threshold. If the returned score value is less than the threshold value, then a no-match event will be triggered. The score values range from 0.0 (completely uncertain) to 1.0 (completely certain). If set to 0.0, the default of 0.3 is used. You can set a separate classification threshold for the flow in each language enabled for the agent. |
model |
Indicates NLU model training mode. |
ModelType
NLU model type.
Enums | |
---|---|
MODEL_TYPE_UNSPECIFIED |
Not specified. MODEL_TYPE_STANDARD will be used. |
MODEL_TYPE_STANDARD |
Use standard NLU model. |
MODEL_TYPE_ADVANCED |
Use advanced NLU model. |
ModelTrainingMode
NLU model training mode.
Enums | |
---|---|
MODEL_TRAINING_MODE_UNSPECIFIED |
Not specified. MODEL_TRAINING_MODE_AUTOMATIC will be used. |
MODEL_TRAINING_MODE_AUTOMATIC |
NLU model training is automatically triggered when a flow gets modified. User can also manually trigger model training in this mode. |
MODEL_TRAINING_MODE_MANUAL |
User needs to manually trigger NLU model training. Best for large flows whose models take long time to train. |