Hi, In NER is there a way to make sure that the model learns the complete pattern and not the sub-pattern.
For example, My training data has the following type of sentences. 1) at 10 - Entire thing tagged 2) at 10 am - Entire thing tagged 3) at 10 cd - Entire thing *untagged* 4) at 10 the meeting - 'at 10' tagged When I test it for the case ' at 10 ab' the model tags 'at 10'. But I don't want this to happen. Could someone plz guide me. Please let me understand what is happening behind. Thanks, Manoj
