explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-21 21:49:49 +03:00
Code Issues Packages Projects Releases Wiki Activity

Only set NORM on Token in retokenizer (#6464)

Browse Source 
* Only set NORM on Token in retokenizer

Instead of setting `NORM` on both the token and lexeme, set `NORM` only
on the token.

The retokenizer tries to set all possible attributes with
`Token/Lexeme.set_struct_attr` so that it doesn't have to enumerate
which attributes are available for each. `NORM` is the only attribute
that's stored on both and for most cases it doesn't make sense to set
the global norms based on a individual retokenization. For lexeme-only
attributes like `IS_STOP` there's no way to avoid the global side
effects, but I think that `NORM` would be better only on the token.

* Fix test
This commit is contained in:
Adriane Boyd 2020-11-30 02:35:42 +01:00 committed by GitHub
parent 03ae77e603
commit 53c0fb7431
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/tests/doc/test_retokenize_merge.py
View File

@ -414,6 +414,13 @@ def test_doc_retokenizer_merge_lex_attrs(en_vocab):
assert doc[1].is_stop assert doc[1].is_stop
assert not doc[0].is_stop assert not doc[0].is_stop
assert not doc[1].like_num assert not doc[1].like_num
# Test that norm is only set on tokens
doc = Doc(en_vocab, words=["eins", "zwei", "!", "!"])
assert doc[0].norm_ == "eins"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:1], attrs={"norm": "1"})
assert doc[0].norm_ == "1"
assert en_vocab["eins"].norm_ == "eins"
def test_retokenize_skip_duplicates(en_vocab): def test_retokenize_skip_duplicates(en_vocab):

12
spacy/tokens/_retokenize.pyx
View File

@ -16,7 +16,7 @@ from .span cimport Span
from .token cimport Token from .token cimport Token
from ..lexeme cimport Lexeme, EMPTY_LEXEME from ..lexeme cimport Lexeme, EMPTY_LEXEME
from ..structs cimport LexemeC, TokenC from ..structs cimport LexemeC, TokenC
from ..attrs cimport TAG from ..attrs cimport TAG, NORM
from .underscore import is_writable_attr from .underscore import is_writable_attr
from ..attrs import intify_attrs from ..attrs import intify_attrs
@ -238,9 +238,10 @@ def _merge(Doc doc, merges):
# Set attributes on both token and lexeme to take care of token # Set attributes on both token and lexeme to take care of token
# attribute vs. lexical attribute without having to enumerate # attribute vs. lexical attribute without having to enumerate
# them. If an attribute name is not valid, set_struct_attr will # them. If an attribute name is not valid, set_struct_attr will
# ignore it. # ignore it. Exception: set NORM only on tokens.
Token.set_struct_attr(token, attr_name, attr_value) Token.set_struct_attr(token, attr_name, attr_value)
Lexeme.set_struct_attr(<LexemeC*>lex, attr_name, attr_value) if attr_name != NORM:
Lexeme.set_struct_attr(<LexemeC*>lex, attr_name, attr_value)
# Begin by setting all the head indices to absolute token positions # Begin by setting all the head indices to absolute token positions
# This is easier to work with for now than the offsets # This is easier to work with for now than the offsets
# Before thinking of something simpler, beware the case where a # Before thinking of something simpler, beware the case where a
@ -393,9 +394,10 @@ def _split(Doc doc, int token_index, orths, heads, attrs):
# Set attributes on both token and lexeme to take care of token # Set attributes on both token and lexeme to take care of token
# attribute vs. lexical attribute without having to enumerate # attribute vs. lexical attribute without having to enumerate
# them. If an attribute name is not valid, set_struct_attr will # them. If an attribute name is not valid, set_struct_attr will
# ignore it. # ignore it. Exception: set NORM only on tokens.
Token.set_struct_attr(token, attr_name, get_string_id(attr_value)) Token.set_struct_attr(token, attr_name, get_string_id(attr_value))
Lexeme.set_struct_attr(<LexemeC*>token.lex, attr_name, get_string_id(attr_value)) if attr_name != NORM:
Lexeme.set_struct_attr(<LexemeC*>token.lex, attr_name, get_string_id(attr_value))
# Assign correct dependencies to the inner token # Assign correct dependencies to the inner token
for i, head in enumerate(heads): for i, head in enumerate(heads):
doc.c[token_index + i].head = head doc.c[token_index + i].head = head