I think in this case spaCy won’t be able to help much. Also, note the question here. The French spaCy model doesn’t seem to be great at finding Arabic names. It’s likely the French model overfits names from France because that’s what it has been trained on.
I’ll be picking this up as a task for rasa-nlu-examples here. Probably the simplest solution is to host the most frequent names per country such that folks can easily link that to a RegexEntityExtractor.
thanks @koaning…i have another issue tho…am trying to get the normalized value of an entity duration that is extracted using duckling but it gives me error i dont know what i did wrong
@koaning
okay here …am trying to get a normalized value of an entity duration that is extracted using duckling but gives me an error and dont know what i did wrong
duration_value = next(tracker.get_latest_entity_values("duration" , None))["entities"]["additional_info"]["normalized"] ```
```diapachter
dispatcher.utter_message(text=int(duration_value))```
```error
Exception occurred while handling uri: 'http://localhost:5055/webhook'
Traceback (most recent call last):
File "c:\programdata\anaconda3\envs\rasabot\lib\site-packages\sanic\app.py", line 976, in handle_request
response = await response
File "C:\Users\hp\AppData\Roaming\Python\Python37\site-packages\rasa_sdk\endpoint.py", line 102, in webhook
result = await executor.run(action_call)
File "C:\Users\hp\AppData\Roaming\Python\Python37\site-packages\rasa_sdk\executor.py", line 390, in run
action(dispatcher, tracker, domain)
File "C:\Users\hp\Documents\faiza\rasa\actions.py", line 202, in run
duration_value = next(tracker.get_latest_entity_values("duration" , None))["entities"]["additional_info"]["normalized"]
TypeError: 'int' object is not subscriptable```