Question

1
Replies
83
Views
 Al Nawab (AlsabahN)
Wipro Ltd

Wipro Ltd
US
AlsabahN Member since 2019 5 posts
Wipro Ltd
Posted: May 9, 2019
Last activity: May 10, 2019
Posted: 9 May 2019 11:29 EDT
Last activity: 10 May 2019 4:36 EDT
Closed

Training Text Analyzer / Topic Detection

Hi,

Use case: Unmatched values are displayed along with list of Topics. The user selects best matched Topic. Using this data I want to train the model to match this value next time.

In my activity I am calling pxCaptureTAFeedback followed by pxUpdateModels. However I do not see expected results.

Do we have any examples /working code that updates NLP model / Text categorization / Topic ?

Thanks

Al

Pega Customer Decision Hub Low-Code App Development Decision Management
Moderation Team has archived post, This thread is closed to future replies. Content and links will no longer be updated. If you have the same/similar Question, please write a new Question.
Posted: 2 years ago
Posted: 10 May 2019 4:36 EDT
Arijit Mitra (mitra2)
PEGA
Senior Product Manager, NLP & Data Science
Pegasystems Inc.
IN

Hello,


The approach is correct.


 


You can also try the same in PredictionStudio/Analytics centre where we can build a Text Categorization model.


You can try out the same in Channels and Interfaces in IVA where you can provide the o/p in Training data tab.


 


Do let me know how many training data you have per topic , for better results please put at least 10 data per topic.