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
Another solution we could have to work with regexes that we are not able to limit with labels or presences of other words may be limiting the words that are used when we filter.
Similar to when we use reduced_words in our detectors, when a word is used in a term, we could set a type: attribute and reduce the pool of words we use when detecting.
The text was updated successfully, but these errors were encountered:
For now we can simply allow for the type attribute to be set and work with examples as they come. I'm sure there are many in the invoice number recognition 😉
Another solution we could have to work with regexes that we are not able to limit with labels or presences of other words may be limiting the words that are used when we filter.
Similar to when we use
reduced_words
in our detectors, when a word is used in a term, we could set atype:
attribute and reduce the pool of words we use when detecting.The text was updated successfully, but these errors were encountered: