mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
fa79a0db9f
* Add AttributeRuler for token attribute exceptions
Add the `AttributeRuler` to handle exceptions for token-level
attributes. The `AttributeRuler` uses `Matcher` patterns to identify
target spans and applies the specified attributes to the token at the
provided index in the matched span. A negative index can be used to
index from the end of the matched span. The retokenizer is used to
"merge" the individual tokens and assign them the provided attributes.
Helper functions can import existing tag maps and morph rules to the
corresponding `Matcher` patterns.
There is an additional minor bug fix for `MORPH` attributes in the
retokenizer to correctly normalize the values and to handle `MORPH`
alongside `_` in an attrs dict.
* Fix default name
* Update name in error message
* Extend AttributeRuler functionality
* Add option to initialize with a dict of AttributeRuler patterns
* Instead of silently discarding overlapping matches (the default
behavior for the retokenizer if only the attrs differ), split the
matches into disjoint sets and retokenize each set separately. This
allows, for instance, one pattern to set the POS and another pattern to
set the lemma. (If two matches modify the same attribute, it looks like
the attrs are applied in the order they were added, but it may not be
deterministic?)
* Improve types
* Sort spans before processing
* Fix index boundaries in Span
* Refactor retokenizer to separate attrs methods
Add top-level `normalize_token_attrs` and `set_token_attrs` methods.
* Update AttributeRuler to use refactored methods
Update `AttributeRuler` to replace use of full retokenizer with only the
relevant methods for normalizing and setting attributes for a single
token.
* Update spacy/pipeline/attributeruler.py
Co-authored-by: Ines Montani <ines@ines.io>
* Make API more similar to EntityRuler
* Add `AttributeRuler.add_patterns` to add patterns from a list of dicts
* Return list of dicts as property `AttributeRuler.patterns`
* Make attrs_unnormed private
* Add test loading patterns from assets
* Revert "Fix index boundaries in Span"
This reverts commit 8f8a5c3386.
* Add Span index boundary checks (#5861)
* Add Span index boundary checks
* Return Span-specific IndexError in all cases
* Simplify and fix if/else
Co-authored-by: Ines Montani <ines@ines.io>
34 lines
891 B
Python
34 lines
891 B
Python
from .attributeruler import AttributeRuler
|
|
from .dep_parser import DependencyParser
|
|
from .entity_linker import EntityLinker
|
|
from .ner import EntityRecognizer
|
|
from .entityruler import EntityRuler
|
|
from .morphologizer import Morphologizer
|
|
from .pipe import Pipe
|
|
from spacy.pipeline.senter import SentenceRecognizer
|
|
from .sentencizer import Sentencizer
|
|
from .simple_ner import SimpleNER
|
|
from .tagger import Tagger
|
|
from .textcat import TextCategorizer
|
|
from .tok2vec import Tok2Vec
|
|
from .functions import merge_entities, merge_noun_chunks, merge_subtokens
|
|
|
|
__all__ = [
|
|
"AttributeRuler",
|
|
"DependencyParser",
|
|
"EntityLinker",
|
|
"EntityRecognizer",
|
|
"EntityRuler",
|
|
"Morphologizer",
|
|
"Pipe",
|
|
"SentenceRecognizer",
|
|
"Sentencizer",
|
|
"SimpleNER",
|
|
"Tagger",
|
|
"TextCategorizer",
|
|
"Tok2Vec",
|
|
"merge_entities",
|
|
"merge_noun_chunks",
|
|
"merge_subtokens",
|
|
]
|