Sentence compare alternate impl #1612
Open
Conversation
This file contains 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
|
Let me know if you would like me to do a code review at any point. I've been holding off since there appears to be test failures and merge conflicts on this branch. I'd be happy to offer any additional insight that I can if it helps. |
|
Requires some insight for sure. I will fix the integration issues but first, this is valid only for languages for which spacy provides vectors. So it goes against the chatterbot philosophy of being independent of language. Then, the equivalent sentence can be found very quickly but after the search function returns, the chatterbot engine still takes an (unacceptably) long time to find the response. I have not had much time to see why but looks like something in the sqlite lookup. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Using word vectors provided by spacy english model "en_core_web_lg" which is a 1 time 1Gb dowload.
Some edits are breaking changes for example the search filters but it is to initiate a discussion on how to create KMeans model 1 time by providing a comparison algorithm access to all data.