When is it appropriate to include multiple classes for a sample text in the training data for IBM Watson Natural Language Classifier?
A
When text is very detailed such that identifying a single class may cause inaccuracies.
B
When experts interpret the same text in different ways, multiple classes support those interpretations.
C
When the text utterances are very similar in nature and we want to mark slight differences using classes
D
When the classifier has been retrained and we want to preserve old classes from a previous training set.
Correct Answer:
B
Reference:
https://www.ibm.com/watson/developercloud/doc/natural-language-classifier/using-your-data.html#structure-of-training-data
(guidelines for good
training)
Show Answer
