mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
06f0a8daa0
* fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
96 lines
3.3 KiB
Python
96 lines
3.3 KiB
Python
from thinc.api import concatenate, reduce_max, reduce_mean, siamese, CauchySimilarity
|
|
|
|
from .pipes import Pipe
|
|
from ..language import component
|
|
from ..util import link_vectors_to_models
|
|
|
|
|
|
@component("sentencizer_hook", assigns=["doc.user_hooks"])
|
|
class SentenceSegmenter(object):
|
|
"""A simple spaCy hook, to allow custom sentence boundary detection logic
|
|
(that doesn't require the dependency parse). To change the sentence
|
|
boundary detection strategy, pass a generator function `strategy` on
|
|
initialization, or assign a new strategy to the .strategy attribute.
|
|
Sentence detection strategies should be generators that take `Doc` objects
|
|
and yield `Span` objects for each sentence.
|
|
"""
|
|
|
|
def __init__(self, vocab, strategy=None):
|
|
self.vocab = vocab
|
|
if strategy is None or strategy == "on_punct":
|
|
strategy = self.split_on_punct
|
|
self.strategy = strategy
|
|
|
|
def __call__(self, doc):
|
|
doc.user_hooks["sents"] = self.strategy
|
|
return doc
|
|
|
|
@staticmethod
|
|
def split_on_punct(doc):
|
|
start = 0
|
|
seen_period = False
|
|
for i, token in enumerate(doc):
|
|
if seen_period and not token.is_punct:
|
|
yield doc[start : token.i]
|
|
start = token.i
|
|
seen_period = False
|
|
elif token.text in [".", "!", "?"]:
|
|
seen_period = True
|
|
if start < len(doc):
|
|
yield doc[start : len(doc)]
|
|
|
|
|
|
@component("similarity", assigns=["doc.user_hooks"])
|
|
class SimilarityHook(Pipe):
|
|
"""
|
|
Experimental: A pipeline component to install a hook for supervised
|
|
similarity into `Doc` objects. Requires a `Tensorizer` to pre-process
|
|
documents. The similarity model can be any object obeying the Thinc `Model`
|
|
interface. By default, the model concatenates the elementwise mean and
|
|
elementwise max of the two tensors, and compares them using the
|
|
Cauchy-like similarity function from Chen (2013):
|
|
|
|
>>> similarity = 1. / (1. + (W * (vec1-vec2)**2).sum())
|
|
|
|
Where W is a vector of dimension weights, initialized to 1.
|
|
"""
|
|
|
|
def __init__(self, vocab, model=True, **cfg):
|
|
self.vocab = vocab
|
|
self.model = model
|
|
self.cfg = dict(cfg)
|
|
|
|
@classmethod
|
|
def Model(cls, length):
|
|
return siamese(
|
|
concatenate(reduce_max(), reduce_mean()), CauchySimilarity(length * 2)
|
|
)
|
|
|
|
def __call__(self, doc):
|
|
"""Install similarity hook"""
|
|
doc.user_hooks["similarity"] = self.predict
|
|
return doc
|
|
|
|
def pipe(self, docs, **kwargs):
|
|
for doc in docs:
|
|
yield self(doc)
|
|
|
|
def predict(self, doc1, doc2):
|
|
return self.model.predict([(doc1, doc2)])
|
|
|
|
def update(self, doc1_doc2, golds, sgd=None, drop=0.0):
|
|
sims, bp_sims = self.model.begin_update(doc1_doc2)
|
|
|
|
def begin_training(self, _=tuple(), pipeline=None, sgd=None, **kwargs):
|
|
"""Allocate model, using width from tensorizer in pipeline.
|
|
|
|
gold_tuples (iterable): Gold-standard training data.
|
|
pipeline (list): The pipeline the model is part of.
|
|
"""
|
|
if self.model is True:
|
|
self.model = self.Model(pipeline[0].model.get_dim("nO"))
|
|
link_vectors_to_models(self.vocab)
|
|
if sgd is None:
|
|
sgd = self.create_optimizer()
|
|
return sgd
|