You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I don't think it's important to break down the results by which spelling variations were used. Can just aggregate all the results for all variations by and label it by what's in the keyword column.
The text was updated successfully, but these errors were encountered:
I'm working on this now but my current understanding is that we will / should not use nltk for the spelling variations part of things. The reason is that we basically have 2 options starting out when it comes to getting raw text from zulip:
a. Get all the data from Zulip, then parse it.
b. Use Zulip's endpoints and query features to query certain keywords, on certain streams, etc.
We've went with (b). I think this is actually the better option simply because Zulip has a rate limit for how much we can query.
Summary
Need to utilize new
spelling_variations
column in the Google Sheet.Additional info
At some point, we should probably refactor to use the NLP library that Stephanie recommended.
I don't think it's important to break down the results by which spelling variations were used. Can just aggregate all the results for all variations by and label it by what's in the
keyword
column.The text was updated successfully, but these errors were encountered: