We would like to use the NLP to automatically detect the language of the emails received from our customers in the our Customer Service (CS) application.
In particular we would like to distinguish the cases when the algorithm uses the fallback language (e.g. English ) from the cases where it detects the same language (english).
Our idea was to disable the fallback language and distinguishing the situations based on the output result of NLP: empty (when it was not able to detect the language) and non-empty (when it detects the language), but in the CS we are not able to disable this option (every time that we enable it, then after the refresh of the rule the checkbox appears checked again).
To disable the fallback language in the Customer Service application, you need to follow these steps:
In the navigation pane of App Studio, click Channels.
In the Current channel interfaces section, click the icon for your existing Email channel.
In the Email channel, click the Behavior tab.
Open the text analyzer rule.
In the text analyzer rule, click the Advanced tab.
In the Language settings section, uncheck the ‘Enable fallback language if the language is undetected’ checkbox.
Click Save.
If the checkbox appears checked again after refreshing the rule, it might be a system issue. In this case, I recommend contacting Pega Support for further assistance.
This is a GenAI-powered tool. All generated answers require validation against the provided references.
This is a GenAI-powered tool. All generated answers require validation against the provided references.