User Profile

Posts

Posts

Post marked as solved
3 Replies
Replied In NLTagger: whimsical lemmatization
Aha. Both "in the weeds" and "we are in the weeds" get lemmatized to "weed". Much better, thanks.Worse, my code was looking at the wrong index, so "IN THE WEEDS" was lemmatizing “IN”. not “WEEDS”. And “Indiana” is not the correct lemmatization here, but it's not insane.
Post not yet marked as solved
2 Replies
Replied In Performance Characteristics of NLTextClassifier
more like an order of magnitude.But the neural network is the network; why would it run more slowly on garbage input than on any other input?
Post not yet marked as solved
3 Replies
Replied In NLTagger errors
NLTaggerOptions provides an option NLTaggerJoinContractions, which might help here. However, I agree that some of the tagging is erratic. It’s quite difficult to know where the limitation lie, or how to cure them, without some insight into what the system is doing.
Post not yet marked as solved
19 Replies
Replied In Create ML templates - only see image and sound
Still nothing, nearly three weeks later.