mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +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>
54 lines
2.2 KiB
Python
54 lines
2.2 KiB
Python
from typing import Union, Iterator
|
|
|
|
from ...symbols import NOUN, PROPN, PRON
|
|
from ...errors import Errors
|
|
from ...tokens import Doc, Span
|
|
|
|
|
|
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Span]:
|
|
"""Detect base noun phrases from a dependency parse. Works on Doc and Span."""
|
|
# It follows the logic of the noun chunks finder of English language,
|
|
# adjusted to some Greek language special characteristics.
|
|
# obj tag corrects some DEP tagger mistakes.
|
|
# Further improvement of the models will eliminate the need for this tag.
|
|
labels = ["nsubj", "obj", "iobj", "appos", "ROOT", "obl"]
|
|
doc = doclike.doc # Ensure works on both Doc and Span.
|
|
if not doc.has_annotation("DEP"):
|
|
raise ValueError(Errors.E029)
|
|
np_deps = [doc.vocab.strings.add(label) for label in labels]
|
|
conj = doc.vocab.strings.add("conj")
|
|
nmod = doc.vocab.strings.add("nmod")
|
|
np_label = doc.vocab.strings.add("NP")
|
|
prev_end = -1
|
|
for i, word in enumerate(doclike):
|
|
if word.pos not in (NOUN, PROPN, PRON):
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.left_edge.i <= prev_end:
|
|
continue
|
|
if word.dep in np_deps:
|
|
flag = False
|
|
if word.pos == NOUN:
|
|
# check for patterns such as γραμμή παραγωγής
|
|
for potential_nmod in word.rights:
|
|
if potential_nmod.dep == nmod:
|
|
prev_end = potential_nmod.i
|
|
yield word.left_edge.i, potential_nmod.i + 1, np_label
|
|
flag = True
|
|
break
|
|
if flag is False:
|
|
prev_end = word.i
|
|
yield word.left_edge.i, word.i + 1, np_label
|
|
elif word.dep == conj:
|
|
# covers the case: έχει όμορφα και έξυπνα παιδιά
|
|
head = word.head
|
|
while head.dep == conj and head.head.i < head.i:
|
|
head = head.head
|
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
|
if head.dep in np_deps:
|
|
prev_end = word.i
|
|
yield word.left_edge.i, word.i + 1, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|