mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
7e4cd7575c
* Refactor Docs.is_ flags
* Add derived `Doc.has_annotation` method
* `Doc.has_annotation(attr)` returns `True` for partial annotation
* `Doc.has_annotation(attr, require_complete=True)` returns `True` for
complete annotation
* Add deprecation warnings to `is_tagged`, `is_parsed`, `is_sentenced`
and `is_nered`
* Add `Doc._get_array_attrs()`, which returns a full list of `Doc` attrs
for use with `Doc.to_array`, `Doc.to_bytes` and `Doc.from_docs`. The
list is the `DocBin` attributes list plus `SPACY` and `LENGTH`.
Notes on `Doc.has_annotation`:
* `HEAD` is converted to `DEP` because heads don't have an unset state
* Accept `IS_SENT_START` as a synonym of `SENT_START`
Additional changes:
* Add `NORM`, `ENT_ID` and `SENT_START` to default attributes for
`DocBin`
* In `Doc.from_array()` the presence of `DEP` causes `HEAD` to override
`SENT_START`
* In `Doc.from_array()` using `attrs` other than
`Doc._get_array_attrs()` (i.e., a user's custom list rather than our
default internal list) with both `HEAD` and `SENT_START` shows a warning
that `HEAD` will override `SENT_START`
* `set_children_from_heads` does not require dependency labels to set
sentence boundaries and sets `sent_start` for all non-sentence starts to
`-1`
* Fix call to set_children_form_heads
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
69 lines
2.2 KiB
Python
69 lines
2.2 KiB
Python
from typing import Union, Iterator, Optional, List, Tuple
|
|
|
|
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
|
|
from ...errors import Errors
|
|
from ...tokens import Doc, Span, Token
|
|
|
|
|
|
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Span]:
|
|
"""Detect base noun phrases from a dependency parse. Works on Doc and Span."""
|
|
doc = doclike.doc
|
|
if not doc.has_annotation("DEP"):
|
|
raise ValueError(Errors.E029)
|
|
if not len(doc):
|
|
return
|
|
np_label = doc.vocab.strings.add("NP")
|
|
left_labels = ["det", "fixed", "neg"] # ['nunmod', 'det', 'appos', 'fixed']
|
|
right_labels = ["flat", "fixed", "compound", "neg"]
|
|
stop_labels = ["punct"]
|
|
np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
|
|
np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
|
|
stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
|
|
for token in doclike:
|
|
if token.pos in [PROPN, NOUN, PRON]:
|
|
left, right = noun_bounds(
|
|
doc, token, np_left_deps, np_right_deps, stop_deps
|
|
)
|
|
yield left.i, right.i + 1, np_label
|
|
token = right
|
|
token = next_token(token)
|
|
|
|
|
|
def is_verb_token(token: Token) -> bool:
|
|
return token.pos in [VERB, AUX]
|
|
|
|
|
|
def next_token(token: Token) -> Optional[Token]:
|
|
try:
|
|
return token.nbor()
|
|
except IndexError:
|
|
return None
|
|
|
|
|
|
def noun_bounds(
|
|
doc: Doc,
|
|
root: Token,
|
|
np_left_deps: List[str],
|
|
np_right_deps: List[str],
|
|
stop_deps: List[str],
|
|
) -> Tuple[Token, Token]:
|
|
left_bound = root
|
|
for token in reversed(list(root.lefts)):
|
|
if token.dep in np_left_deps:
|
|
left_bound = token
|
|
right_bound = root
|
|
for token in root.rights:
|
|
if token.dep in np_right_deps:
|
|
left, right = noun_bounds(
|
|
doc, token, np_left_deps, np_right_deps, stop_deps
|
|
)
|
|
filter_func = lambda t: is_verb_token(t) or t.dep in stop_deps
|
|
if list(filter(filter_func, doc[left_bound.i : right.i],)):
|
|
break
|
|
else:
|
|
right_bound = right
|
|
return left_bound, right_bound
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|