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
Named entities ending with s will be treated by the lemmatizer as if they are plurals, e.g. Bernie Sanders turns into bernie sander, ISIS becomes isi, United States becomes united state. It probably also applies to other suffixes.
This may be intentional, so maybe adding a flag would be a good solution. Or is there another work around?
[Update] Somewhat related: when something like CIA is at the end of a sentence, the named entity becomes CIA.. My guess is that this is done to account for acronyms like A.M., but the trend seems to be to eliminate periods from acronyms, so punctuation can probably be stripped from the Named Entity altogether (avoiding the inconsistency).
The text was updated successfully, but these errors were encountered:
…n't receiving the PROPN tag, and personal pronouns weren't receiving the PRON tag. This should fix Issue #191, and also Issue #325, which reported that proper nouns were being lemmatized using the common noun policies. This lemmatization will be prevented if the universal tag is PROPN, not NOUN, as no lemmatization rules are loaded for the PROPN tag.
Named entities ending with
s
will be treated by the lemmatizer as if they are plurals, e.g.Bernie Sanders
turns intobernie sander
,ISIS
becomesisi
,United States
becomesunited state
. It probably also applies to other suffixes.This may be intentional, so maybe adding a flag would be a good solution. Or is there another work around?
[Update] Somewhat related: when something like
CIA
is at the end of a sentence, the named entity becomesCIA.
. My guess is that this is done to account for acronyms likeA.M.
, but the trend seems to be to eliminate periods from acronyms, so punctuation can probably be stripped from the Named Entity altogether (avoiding the inconsistency).The text was updated successfully, but these errors were encountered: