explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-15 02:32:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Adjust NER rules, so that U entries in gazetteer don't become B moves to the model

Browse Source
This commit is contained in:
Matthew Honnibal 2015-11-12 04:48:23 +11:00
parent 6e68b344c1
commit 5623242b3e
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/syntax/ner.pyx
View File

@ -173,6 +173,10 @@ cdef class Begin:
# If the next word is B or O, we can't B now # If the next word is B or O, we can't B now
elif st.B_(1).ent_iob == 2 or st.B_(1).ent_iob == 3: elif st.B_(1).ent_iob == 2 or st.B_(1).ent_iob == 3:
return False return False
# If the current word is B, and the next word isn't I, the current word
# is really U
elif preset_ent_iob == 3 and st.B_(1).ent_iob != 1:
return False
# Don't allow entities to extend across sentence boundaries # Don't allow entities to extend across sentence boundaries
elif st.B_(1).sent_start: elif st.B_(1).sent_start:
return False return False