2020-07-22 11:42:59 +00:00
|
|
|
# cython: infer_types=True, profile=True, binding=True
|
|
|
|
from typing import Optional, Iterable
|
|
|
|
from thinc.api import CosineDistance, to_categorical, get_array_module, Model, Config
|
|
|
|
|
|
|
|
from ..syntax.nn_parser cimport Parser
|
|
|
|
from ..syntax.ner cimport BiluoPushDown
|
|
|
|
|
|
|
|
from ..language import Language
|
Refactor the Scorer to improve flexibility (#5731)
* Refactor the Scorer to improve flexibility
Refactor the `Scorer` to improve flexibility for arbitrary pipeline
components.
* Individual pipeline components provide their own `evaluate` methods
that score a list of `Example`s and return a dictionary of scores
* `Scorer` is initialized either:
* with a provided pipeline containing components to be scored
* with a default pipeline containing the built-in statistical
components (senter, tagger, morphologizer, parser, ner)
* `Scorer.score` evaluates a list of `Example`s and returns a dictionary
of scores referring to the scores provided by the components in the
pipeline
Significant differences:
* `tags_acc` is renamed to `tag_acc` to be consistent with `token_acc`
and the new `morph_acc`, `pos_acc`, and `lemma_acc`
* Scoring is no longer cumulative: `Scorer.score` scores a list of
examples rather than a single example and does not retain any state
about previously scored examples
* PRF values in the returned scores are no longer multiplied by 100
* Add kwargs to Morphologizer.evaluate
* Create generalized scoring methods in Scorer
* Generalized static scoring methods are added to `Scorer`
* Methods require an attribute (either on Token or Doc) that is
used to key the returned scores
Naming differences:
* `uas`, `las`, and `las_per_type` in the scores dict are renamed to
`dep_uas`, `dep_las`, and `dep_las_per_type`
Scoring differences:
* `Doc.sents` is now scored as spans rather than on sentence-initial
token positions so that `Doc.sents` and `Doc.ents` can be scored with
the same method (this lowers scores since a single incorrect sentence
start results in two incorrect spans)
* Simplify / extend hasattr check for eval method
* Add hasattr check to tokenizer scoring
* Simplify to hasattr check for component scoring
* Reset Example alignment if docs are set
Reset the Example alignment if either doc is set in case the
tokenization has changed.
* Add PRF tokenization scoring for tokens as spans
Add PRF scores for tokens as character spans. The scores are:
* token_acc: # correct tokens / # gold tokens
* token_p/r/f: PRF for (token.idx, token.idx + len(token))
* Add docstring to Scorer.score_tokenization
* Rename component.evaluate() to component.score()
* Update Scorer API docs
* Update scoring for positive_label in textcat
* Fix TextCategorizer.score kwargs
* Update Language.evaluate docs
* Update score names in default config
2020-07-25 10:53:02 +00:00
|
|
|
from ..scorer import Scorer
|
2020-07-22 11:42:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
default_model_config = """
|
|
|
|
[model]
|
|
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
|
|
nr_feature_tokens = 6
|
|
|
|
hidden_width = 64
|
|
|
|
maxout_pieces = 2
|
|
|
|
|
|
|
|
[model.tok2vec]
|
|
|
|
@architectures = "spacy.HashEmbedCNN.v1"
|
|
|
|
pretrained_vectors = null
|
|
|
|
width = 96
|
|
|
|
depth = 4
|
|
|
|
embed_size = 2000
|
|
|
|
window_size = 1
|
|
|
|
maxout_pieces = 3
|
|
|
|
subword_features = true
|
|
|
|
dropout = null
|
|
|
|
"""
|
|
|
|
DEFAULT_NER_MODEL = Config().from_str(default_model_config)["model"]
|
|
|
|
|
|
|
|
|
|
|
|
@Language.factory(
|
|
|
|
"ner",
|
|
|
|
assigns=["doc.ents", "token.ent_iob", "token.ent_type"],
|
|
|
|
default_config={
|
|
|
|
"moves": None,
|
|
|
|
"update_with_oracle_cut_size": 100,
|
|
|
|
"multitasks": [],
|
|
|
|
"learn_tokens": False,
|
|
|
|
"min_action_freq": 30,
|
|
|
|
"model": DEFAULT_NER_MODEL,
|
2020-07-26 11:18:43 +00:00
|
|
|
},
|
|
|
|
scores=["ents_f", "ents_r", "ents_p"],
|
|
|
|
score_weights={"ents_f": 1.0, "ents_r": 0.0, "ents_p": 0.0},
|
2020-07-22 11:42:59 +00:00
|
|
|
)
|
|
|
|
def make_ner(
|
|
|
|
nlp: Language,
|
|
|
|
name: str,
|
|
|
|
model: Model,
|
|
|
|
moves: Optional[list],
|
|
|
|
update_with_oracle_cut_size: int,
|
|
|
|
multitasks: Iterable,
|
|
|
|
learn_tokens: bool,
|
|
|
|
min_action_freq: int
|
|
|
|
):
|
|
|
|
return EntityRecognizer(
|
|
|
|
nlp.vocab,
|
|
|
|
model,
|
|
|
|
name,
|
|
|
|
moves=moves,
|
|
|
|
update_with_oracle_cut_size=update_with_oracle_cut_size,
|
|
|
|
multitasks=multitasks,
|
|
|
|
learn_tokens=learn_tokens,
|
|
|
|
min_action_freq=min_action_freq
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
cdef class EntityRecognizer(Parser):
|
|
|
|
"""Pipeline component for named entity recognition.
|
|
|
|
|
|
|
|
DOCS: https://spacy.io/api/entityrecognizer
|
|
|
|
"""
|
|
|
|
TransitionSystem = BiluoPushDown
|
|
|
|
|
|
|
|
def add_multitask_objective(self, mt_component):
|
|
|
|
self._multitasks.append(mt_component)
|
|
|
|
|
|
|
|
def init_multitask_objectives(self, get_examples, pipeline, sgd=None, **cfg):
|
|
|
|
# TODO: transfer self.model.get_ref("tok2vec") to the multitask's model ?
|
|
|
|
for labeller in self._multitasks:
|
|
|
|
labeller.model.set_dim("nO", len(self.labels))
|
|
|
|
if labeller.model.has_ref("output_layer"):
|
|
|
|
labeller.model.get_ref("output_layer").set_dim("nO", len(self.labels))
|
|
|
|
labeller.begin_training(get_examples, pipeline=pipeline)
|
|
|
|
|
|
|
|
@property
|
|
|
|
def labels(self):
|
|
|
|
# Get the labels from the model by looking at the available moves, e.g.
|
|
|
|
# B-PERSON, I-PERSON, L-PERSON, U-PERSON
|
|
|
|
labels = set(move.split("-")[1] for move in self.move_names
|
|
|
|
if move[0] in ("B", "I", "L", "U"))
|
|
|
|
return tuple(sorted(labels))
|
Refactor the Scorer to improve flexibility (#5731)
* Refactor the Scorer to improve flexibility
Refactor the `Scorer` to improve flexibility for arbitrary pipeline
components.
* Individual pipeline components provide their own `evaluate` methods
that score a list of `Example`s and return a dictionary of scores
* `Scorer` is initialized either:
* with a provided pipeline containing components to be scored
* with a default pipeline containing the built-in statistical
components (senter, tagger, morphologizer, parser, ner)
* `Scorer.score` evaluates a list of `Example`s and returns a dictionary
of scores referring to the scores provided by the components in the
pipeline
Significant differences:
* `tags_acc` is renamed to `tag_acc` to be consistent with `token_acc`
and the new `morph_acc`, `pos_acc`, and `lemma_acc`
* Scoring is no longer cumulative: `Scorer.score` scores a list of
examples rather than a single example and does not retain any state
about previously scored examples
* PRF values in the returned scores are no longer multiplied by 100
* Add kwargs to Morphologizer.evaluate
* Create generalized scoring methods in Scorer
* Generalized static scoring methods are added to `Scorer`
* Methods require an attribute (either on Token or Doc) that is
used to key the returned scores
Naming differences:
* `uas`, `las`, and `las_per_type` in the scores dict are renamed to
`dep_uas`, `dep_las`, and `dep_las_per_type`
Scoring differences:
* `Doc.sents` is now scored as spans rather than on sentence-initial
token positions so that `Doc.sents` and `Doc.ents` can be scored with
the same method (this lowers scores since a single incorrect sentence
start results in two incorrect spans)
* Simplify / extend hasattr check for eval method
* Add hasattr check to tokenizer scoring
* Simplify to hasattr check for component scoring
* Reset Example alignment if docs are set
Reset the Example alignment if either doc is set in case the
tokenization has changed.
* Add PRF tokenization scoring for tokens as spans
Add PRF scores for tokens as character spans. The scores are:
* token_acc: # correct tokens / # gold tokens
* token_p/r/f: PRF for (token.idx, token.idx + len(token))
* Add docstring to Scorer.score_tokenization
* Rename component.evaluate() to component.score()
* Update Scorer API docs
* Update scoring for positive_label in textcat
* Fix TextCategorizer.score kwargs
* Update Language.evaluate docs
* Update score names in default config
2020-07-25 10:53:02 +00:00
|
|
|
|
|
|
|
def score(self, examples, **kwargs):
|
|
|
|
return Scorer.score_spans(examples, "ents", **kwargs)
|