mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
f9946154d9
* Draft spancat model
* Add spancat model
* Add test for extract_spans
* Add extract_spans layer
* Upd extract_spans
* Add spancat model
* Add test for spancat model
* Upd spancat model
* Update spancat component
* Upd spancat
* Update spancat model
* Add quick spancat test
* Import SpanCategorizer
* Fix SpanCategorizer component
* Import SpanGroup
* Fix span extraction
* Fix import
* Fix import
* Upd model
* Update spancat models
* Add scoring, update defaults
* Update and add docs
* Fix type
* Update spacy/ml/extract_spans.py
* Auto-format and fix import
* Fix comment
* Fix type
* Fix type
* Update website/docs/api/spancategorizer.md
* Fix comment
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Better defense
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Fix labels list
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Update spacy/ml/extract_spans.py
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Update spacy/pipeline/spancat.py
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Set annotations during update
* Set annotations in spancat
* fix imports in test
* Update spacy/pipeline/spancat.py
* replace MaxoutLogistic with LinearLogistic
* fix config
* various small fixes
* remove set_annotations parameter in update
* use our beloved tupley format with recent support for doc.spans
* bugfix to allow renaming the default span_key (scores weren't showing up)
* use different key in docs example
* change defaults to better-working parameters from project (WIP)
* register spacy.extract_spans.v1 for legacy purposes
* Upd dev version so can build wheel
* layers instead of architectures for smaller building blocks
* Update website/docs/api/spancategorizer.md
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Update website/docs/api/spancategorizer.md
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Include additional scores from overrides in combined score weights
* Parameterize spans key in scoring
Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so
that it's possible to evaluate multiple `spancat` components in the same
pipeline.
* Use the (intentionally very short) default spans key `sc` in the
`SpanCategorizer`
* Adjust the default score weights to include the default key
* Adjust the scorer to use `spans_{spans_key}` as the prefix for the
returned score
* Revert addition of `attr_name` argument to `score_spans` and adjust
the key in the `getter` instead.
Note that for `spancat` components with a custom `span_key`, the score
weights currently need to be modified manually in
`[training.score_weights]` for them to be available during training. To
suppress the default score weights `spans_sc_p/r/f` during training, set
them to `null` in `[training.score_weights]`.
* Update website/docs/api/scorer.md
* Fix scorer for spans key containing underscore
* Increment version
* Add Spans to Evaluate CLI (#8439)
* Add Spans to Evaluate CLI
* Change to spans_key
* Add spans per_type output
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Fix spancat GPU issues (#8455)
* Fix GPU issues
* Require thinc >=8.0.6
* Switch to glorot_uniform_init
* Fix and test ngram suggester
* Include final ngram in doc for all sizes
* Fix ngrams for docs of the same length as ngram size
* Handle batches of docs that result in no ngrams
* Add tests
Co-authored-by: Ines Montani <ines@ines.io>
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: Nirant <NirantK@users.noreply.github.com>
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
from .attributeruler import AttributeRuler
|
|
from .dep_parser import DependencyParser
|
|
from .entity_linker import EntityLinker
|
|
from .ner import EntityRecognizer
|
|
from .entityruler import EntityRuler
|
|
from .lemmatizer import Lemmatizer
|
|
from .morphologizer import Morphologizer
|
|
from .pipe import Pipe
|
|
from .trainable_pipe import TrainablePipe
|
|
from .senter import SentenceRecognizer
|
|
from .sentencizer import Sentencizer
|
|
from .tagger import Tagger
|
|
from .textcat import TextCategorizer
|
|
from .spancat import SpanCategorizer
|
|
from .textcat_multilabel import MultiLabel_TextCategorizer
|
|
from .tok2vec import Tok2Vec
|
|
from .functions import merge_entities, merge_noun_chunks, merge_subtokens
|
|
|
|
__all__ = [
|
|
"AttributeRuler",
|
|
"DependencyParser",
|
|
"EntityLinker",
|
|
"EntityRecognizer",
|
|
"EntityRuler",
|
|
"Morphologizer",
|
|
"Lemmatizer",
|
|
"MultiLabel_TextCategorizer",
|
|
"Pipe",
|
|
"SentenceRecognizer",
|
|
"Sentencizer",
|
|
"SpanCategorizer",
|
|
"Tagger",
|
|
"TextCategorizer",
|
|
"Tok2Vec",
|
|
"TrainablePipe",
|
|
"merge_entities",
|
|
"merge_noun_chunks",
|
|
"merge_subtokens",
|
|
]
|