Adding a "noMatch" result #7
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
April 12, 2017 11:13
If the networks outputs a value under 0.9, the result will be "noMatch", wich means two things : 1- the network wasn't able to classify the input, so it might be a new intent or a random string. 2- If it's a false negative, you need to train the network with more strings After tests, 0.9 seems to be a good value, but it can be changed. I'm working on chatbots ( a lot ) so I'm trying to add my knowledge of the tools needed and the usage of them to make this module a better one.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
1- check my last commit for the context of this
2- the networks ouputs a string of value "noMatch" if it's not confident enough
3- the networks must return a value of 0.9 to be sure that it matches
4- it blocks false positives
5- it might send false negatives but it just means that the networks need more training
6- it's now a more useful module for chatbots maker, but it might not be your goal to make it a tool for them.
So that's your turn now.
Nice work BTW, this is the best NLP module that I found !