Merge pull request #6691 from svlandeg/feature/missing-dep

This commit is contained in:
Ines Montani 2021-01-15 11:43:36 +11:00 committed by GitHub
commit 8ba5d88b4b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
14 changed files with 221 additions and 57 deletions

View File

@ -12,6 +12,7 @@ from ..training import Example
from ..training.initialize import get_sourced_components
from ..schemas import ConfigSchemaTraining
from ..pipeline._parser_internals import nonproj
from ..pipeline._parser_internals.nonproj import DELIMITER
from ..language import Language
from ..util import registry, resolve_dot_names
from .. import util
@ -383,7 +384,7 @@ def debug_data(
# rare labels in projectivized train
rare_projectivized_labels = []
for label in gold_train_data["deps"]:
if gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD and "||" in label:
if gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD and DELIMITER in label:
rare_projectivized_labels.append(
f"{label}: {gold_train_data['deps'][label]}"
)

View File

@ -9,6 +9,7 @@ from ...typedefs cimport hash_t, attr_t
from ...strings cimport hash_string
from ...structs cimport TokenC
from ...tokens.doc cimport Doc, set_children_from_heads
from ...tokens.token cimport MISSING_DEP
from ...training.example cimport Example
from .stateclass cimport StateClass
from ._state cimport StateC, ArcC
@ -195,8 +196,7 @@ cdef class ArcEagerGold:
def __init__(self, ArcEager moves, StateClass stcls, Example example):
self.mem = Pool()
heads, labels = example.get_aligned_parse(projectivize=True)
labels = [label if label is not None else "" for label in labels]
labels = [example.x.vocab.strings.add(label) for label in labels]
labels = [example.x.vocab.strings.add(label) if label is not None else MISSING_DEP for label in labels]
sent_starts = example.get_aligned_sent_starts()
assert len(heads) == len(labels) == len(sent_starts), (len(heads), len(labels), len(sent_starts))
self.c = create_gold_state(self.mem, stcls.c, heads, labels, sent_starts)
@ -783,7 +783,7 @@ cdef class ArcEager(TransitionSystem):
for i in range(self.n_moves):
print(self.get_class_name(i), is_valid[i], costs[i])
print("Gold sent starts?", is_sent_start(&gold_state, state.B(0)), is_sent_start(&gold_state, state.B(1)))
raise ValueError
raise ValueError("Could not find gold transition - see logs above.")
def get_oracle_sequence_from_state(self, StateClass state, ArcEagerGold gold, _debug=None):
cdef int i

View File

@ -9,6 +9,7 @@ from ._parser_internals.arc_eager cimport ArcEager
from .functions import merge_subtokens
from ..language import Language
from ._parser_internals import nonproj
from ._parser_internals.nonproj import DELIMITER
from ..scorer import Scorer
from ..training import validate_examples
@ -230,8 +231,8 @@ cdef class DependencyParser(Parser):
for move in self.move_names:
if "-" in move:
label = move.split("-")[1]
if "||" in label:
label = label.split("||")[1]
if DELIMITER in label:
label = label.split(DELIMITER)[1]
labels.add(label)
return tuple(sorted(labels))

View File

@ -89,8 +89,9 @@ def test_doc_retokenize_lex_attrs(en_tokenizer):
def test_doc_retokenize_spans_merge_tokens(en_tokenizer):
text = "Los Angeles start."
heads = [1, 2, 2, 2]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
assert len(doc) == 4
assert doc[0].head.text == "Angeles"
assert doc[1].head.text == "start"
@ -145,7 +146,8 @@ def test_doc_retokenize_spans_merge_tokens_default_attrs(en_vocab):
def test_doc_retokenize_spans_merge_heads(en_vocab):
words = ["I", "found", "a", "pilates", "class", "near", "work", "."]
heads = [1, 1, 4, 6, 1, 4, 5, 1]
doc = Doc(en_vocab, words=words, heads=heads)
deps = ["dep"] * len(heads)
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
assert len(doc) == 8
with doc.retokenize() as retokenizer:
attrs = {"tag": doc[4].tag_, "lemma": "pilates class", "ent_type": "O"}
@ -177,8 +179,9 @@ def test_doc_retokenize_spans_merge_non_disjoint(en_tokenizer):
def test_doc_retokenize_span_np_merges(en_tokenizer):
text = "displaCy is a parse tool built with Javascript"
heads = [1, 1, 4, 4, 1, 4, 5, 6]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
assert doc[4].head.i == 1
with doc.retokenize() as retokenizer:
attrs = {"tag": "NP", "lemma": "tool", "ent_type": "O"}

View File

@ -6,7 +6,8 @@ from spacy.tokens import Doc, Token
def test_doc_retokenize_split(en_vocab):
words = ["LosAngeles", "start", "."]
heads = [1, 2, 2]
doc = Doc(en_vocab, words=words, heads=heads)
deps = ["dep"] * len(heads)
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
assert len(doc) == 3
assert len(str(doc)) == 19
assert doc[0].head.text == "start"

View File

@ -4,6 +4,7 @@ from spacy.attrs import IS_ALPHA, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_TITLE, IS_STO
from spacy.symbols import VERB
from spacy.vocab import Vocab
from spacy.tokens import Doc
from spacy.training import Example
@pytest.fixture
@ -250,3 +251,38 @@ def test_token_api_non_conjuncts(en_vocab):
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
assert [w.text for w in doc[0].conjuncts] == []
assert [w.text for w in doc[1].conjuncts] == []
def test_missing_head_dep(en_vocab):
""" Check that the Doc constructor and Example.from_dict parse missing information the same"""
heads = [1, 1, 1, 1, 2, None] # element 5 is missing
deps = ["", "ROOT", "dobj", "cc", "conj", None] # element 0 and 5 are missing
words = ["I", "like", "London", "and", "Berlin", "."]
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
pred_has_heads = [t.has_head() for t in doc]
pred_has_deps = [t.has_dep() for t in doc]
pred_heads = [t.head.i for t in doc]
pred_deps = [t.dep_ for t in doc]
pred_sent_starts = [t.is_sent_start for t in doc]
assert pred_has_heads == [False, True, True, True, True, False]
assert pred_has_deps == [False, True, True, True, True, False]
assert pred_heads[1:5] == [1, 1, 1, 2]
assert pred_deps[1:5] == ["ROOT", "dobj", "cc", "conj"]
assert pred_sent_starts == [True, False, False, False, False, False]
example = Example.from_dict(doc, {"heads": heads, "deps": deps})
ref_has_heads = [t.has_head() for t in example.reference]
ref_has_deps = [t.has_dep() for t in example.reference]
ref_heads = [t.head.i for t in example.reference]
ref_deps = [t.dep_ for t in example.reference]
ref_sent_starts = [t.is_sent_start for t in example.reference]
assert ref_has_heads == pred_has_heads
assert ref_has_deps == pred_has_heads
assert ref_heads == pred_heads
assert ref_deps == pred_deps
assert ref_sent_starts == pred_sent_starts
# check that the aligned parse preserves the missing information
aligned_heads, aligned_deps = example.get_aligned_parse(projectivize=True)
assert aligned_deps[0] == ref_deps[0]
assert aligned_heads[0] == ref_heads[0]
assert aligned_deps[5] == ref_deps[5]
assert aligned_heads[5] == ref_heads[5]

View File

@ -121,7 +121,7 @@ def test_parser_pseudoprojectivity(en_vocab):
assert undeco_labels == ["det", "nsubj", "root", "det", "dobj", "aux",
"nsubj", "acl", "punct"]
# if there are two potential new heads, the first one is chosen even if
# it"s wrong
# it's wrong
proj_heads = [1, 1, 3, 1, 5, 6, 9, 8, 6, 1, 9, 12, 13, 10, 1]
deco_labels = ["advmod||aux", "root", "det", "aux", "advmod", "det",
"dobj", "det", "nmod", "aux", "nmod||dobj", "advmod",

View File

@ -45,7 +45,17 @@ CONFLICTING_DATA = [
),
]
eps = 0.01
PARTIAL_DATA = [
(
"I like London.",
{
"heads": [1, 1, 1, None],
"deps": ["nsubj", "ROOT", "dobj", None],
},
),
]
eps = 0.1
def test_parser_root(en_vocab):
@ -205,6 +215,32 @@ def test_parser_set_sent_starts(en_vocab):
assert token.head in sent
@pytest.mark.parametrize("pipe_name", ["parser", "beam_parser"])
def test_incomplete_data(pipe_name):
# Test that the parser works with incomplete information
nlp = English()
parser = nlp.add_pipe(pipe_name)
train_examples = []
for text, annotations in PARTIAL_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
for dep in annotations.get("deps", []):
if dep is not None:
parser.add_label(dep)
optimizer = nlp.initialize(get_examples=lambda: train_examples)
for i in range(150):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses[pipe_name] < 0.0001
# test the trained model
test_text = "I like securities."
doc = nlp(test_text)
assert doc[0].dep_ == "nsubj"
assert doc[2].dep_ == "dobj"
assert doc[0].head.i == 1
assert doc[2].head.i == 1
@pytest.mark.parametrize("pipe_name", ["parser", "beam_parser"])
def test_overfitting_IO(pipe_name):
# Simple test to try and quickly overfit the dependency parser (normal or beam)
@ -217,7 +253,7 @@ def test_overfitting_IO(pipe_name):
parser.add_label(dep)
optimizer = nlp.initialize()
# run overfitting
for i in range(150):
for i in range(200):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses[pipe_name] < 0.0001
@ -324,25 +360,25 @@ def test_beam_overfitting_IO():
head_scores = head_scores[0]
label_scores = label_scores[0]
# test label annotations: 0=nsubj, 2=dobj, 3=punct
assert label_scores[(0, "nsubj")] == pytest.approx(1.0, eps)
assert label_scores[(0, "dobj")] == pytest.approx(0.0, eps)
assert label_scores[(0, "punct")] == pytest.approx(0.0, eps)
assert label_scores[(2, "nsubj")] == pytest.approx(0.0, eps)
assert label_scores[(2, "dobj")] == pytest.approx(1.0, eps)
assert label_scores[(2, "punct")] == pytest.approx(0.0, eps)
assert label_scores[(3, "nsubj")] == pytest.approx(0.0, eps)
assert label_scores[(3, "dobj")] == pytest.approx(0.0, eps)
assert label_scores[(3, "punct")] == pytest.approx(1.0, eps)
assert label_scores[(0, "nsubj")] == pytest.approx(1.0, abs=eps)
assert label_scores[(0, "dobj")] == pytest.approx(0.0, abs=eps)
assert label_scores[(0, "punct")] == pytest.approx(0.0, abs=eps)
assert label_scores[(2, "nsubj")] == pytest.approx(0.0, abs=eps)
assert label_scores[(2, "dobj")] == pytest.approx(1.0, abs=eps)
assert label_scores[(2, "punct")] == pytest.approx(0.0, abs=eps)
assert label_scores[(3, "nsubj")] == pytest.approx(0.0, abs=eps)
assert label_scores[(3, "dobj")] == pytest.approx(0.0, abs=eps)
assert label_scores[(3, "punct")] == pytest.approx(1.0, abs=eps)
# test head annotations: the root is token at index 1
assert head_scores[(0, 0)] == pytest.approx(0.0, eps)
assert head_scores[(0, 1)] == pytest.approx(1.0, eps)
assert head_scores[(0, 2)] == pytest.approx(0.0, eps)
assert head_scores[(2, 0)] == pytest.approx(0.0, eps)
assert head_scores[(2, 1)] == pytest.approx(1.0, eps)
assert head_scores[(2, 2)] == pytest.approx(0.0, eps)
assert head_scores[(3, 0)] == pytest.approx(0.0, eps)
assert head_scores[(3, 1)] == pytest.approx(1.0, eps)
assert head_scores[(3, 2)] == pytest.approx(0.0, eps)
assert head_scores[(0, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores[(0, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores[(0, 2)] == pytest.approx(0.0, abs=eps)
assert head_scores[(2, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores[(2, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores[(2, 2)] == pytest.approx(0.0, abs=eps)
assert head_scores[(3, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores[(3, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores[(3, 2)] == pytest.approx(0.0, abs=eps)
# Also test the results are still the same after IO
with make_tempdir() as tmp_dir:
@ -356,21 +392,21 @@ def test_beam_overfitting_IO():
head_scores2 = head_scores2[0]
label_scores2 = label_scores2[0]
# check the results again
assert label_scores2[(0, "nsubj")] == pytest.approx(1.0, eps)
assert label_scores2[(0, "dobj")] == pytest.approx(0.0, eps)
assert label_scores2[(0, "punct")] == pytest.approx(0.0, eps)
assert label_scores2[(2, "nsubj")] == pytest.approx(0.0, eps)
assert label_scores2[(2, "dobj")] == pytest.approx(1.0, eps)
assert label_scores2[(2, "punct")] == pytest.approx(0.0, eps)
assert label_scores2[(3, "nsubj")] == pytest.approx(0.0, eps)
assert label_scores2[(3, "dobj")] == pytest.approx(0.0, eps)
assert label_scores2[(3, "punct")] == pytest.approx(1.0, eps)
assert head_scores2[(0, 0)] == pytest.approx(0.0, eps)
assert head_scores2[(0, 1)] == pytest.approx(1.0, eps)
assert head_scores2[(0, 2)] == pytest.approx(0.0, eps)
assert head_scores2[(2, 0)] == pytest.approx(0.0, eps)
assert head_scores2[(2, 1)] == pytest.approx(1.0, eps)
assert head_scores2[(2, 2)] == pytest.approx(0.0, eps)
assert head_scores2[(3, 0)] == pytest.approx(0.0, eps)
assert head_scores2[(3, 1)] == pytest.approx(1.0, eps)
assert head_scores2[(3, 2)] == pytest.approx(0.0, eps)
assert label_scores2[(0, "nsubj")] == pytest.approx(1.0, abs=eps)
assert label_scores2[(0, "dobj")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(0, "punct")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(2, "nsubj")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(2, "dobj")] == pytest.approx(1.0, abs=eps)
assert label_scores2[(2, "punct")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(3, "nsubj")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(3, "dobj")] == pytest.approx(0.0, abs=eps)
assert label_scores2[(3, "punct")] == pytest.approx(1.0, abs=eps)
assert head_scores2[(0, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores2[(0, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores2[(0, 2)] == pytest.approx(0.0, abs=eps)
assert head_scores2[(2, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores2[(2, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores2[(2, 2)] == pytest.approx(0.0, abs=eps)
assert head_scores2[(3, 0)] == pytest.approx(0.0, abs=eps)
assert head_scores2[(3, 1)] == pytest.approx(1.0, abs=eps)
assert head_scores2[(3, 2)] == pytest.approx(0.0, abs=eps)

View File

@ -263,3 +263,43 @@ def test_Example_from_dict_sentences():
annots = {"sent_starts": [1, -1, 0, 0, 0]}
ex = Example.from_dict(predicted, annots)
assert len(list(ex.reference.sents)) == 1
def test_Example_missing_deps():
vocab = Vocab()
words = ["I", "like", "London", "and", "Berlin", "."]
deps = ["nsubj", "ROOT", "dobj", "cc", "conj", "punct"]
heads = [1, 1, 1, 2, 2, 1]
annots_head_only = {"words": words, "heads": heads}
annots_head_dep = {"words": words, "heads": heads, "deps": deps}
predicted = Doc(vocab, words=words)
# when not providing deps, the head information is considered to be missing
# in this case, the token's heads refer to themselves
example_1 = Example.from_dict(predicted, annots_head_only)
assert [t.head.i for t in example_1.reference] == [0, 1, 2, 3, 4, 5]
# when providing deps, the head information is actually used
example_2 = Example.from_dict(predicted, annots_head_dep)
assert [t.head.i for t in example_2.reference] == heads
def test_Example_missing_heads():
vocab = Vocab()
words = ["I", "like", "London", "and", "Berlin", "."]
deps = ["nsubj", "ROOT", "dobj", None, "conj", "punct"]
heads = [1, 1, 1, None, 2, 1]
annots = {"words": words, "heads": heads, "deps": deps}
predicted = Doc(vocab, words=words)
example = Example.from_dict(predicted, annots)
parsed_heads = [t.head.i for t in example.reference]
assert parsed_heads[0] == heads[0]
assert parsed_heads[1] == heads[1]
assert parsed_heads[2] == heads[2]
assert parsed_heads[4] == heads[4]
assert parsed_heads[5] == heads[5]
assert [t.has_head() for t in example.reference] == [True, True, True, False, True, True]
# Ensure that the missing head doesn't create an artificial new sentence start
assert example.get_aligned_sent_starts() == [True, False, False, False, False, False]

View File

@ -436,7 +436,8 @@ def test_gold_ner_missing_tags(en_tokenizer):
def test_projectivize(en_tokenizer):
doc = en_tokenizer("He pretty quickly walks away")
heads = [3, 2, 3, 0, 2]
example = Example.from_dict(doc, {"heads": heads})
deps = ["dep"] * len(heads)
example = Example.from_dict(doc, {"heads": heads, "deps": deps})
proj_heads, proj_labels = example.get_aligned_parse(projectivize=True)
nonproj_heads, nonproj_labels = example.get_aligned_parse(projectivize=False)
assert proj_heads == [3, 2, 3, 0, 3]

View File

@ -16,6 +16,7 @@ from thinc.util import copy_array
import warnings
from .span cimport Span
from .token cimport MISSING_DEP
from ._dict_proxies import SpanGroups
from .token cimport Token
from ..lexeme cimport Lexeme, EMPTY_LEXEME
@ -268,7 +269,10 @@ cdef class Doc:
self.push_back(lexeme, has_space)
if heads is not None:
heads = [head - i for i, head in enumerate(heads)]
heads = [head - i if head is not None else 0 for i, head in enumerate(heads)]
if deps is not None:
MISSING_DEP_ = self.vocab.strings[MISSING_DEP]
deps = [dep if dep is not None else MISSING_DEP_ for dep in deps]
if deps and not heads:
heads = [0] * len(deps)
if sent_starts is not None:
@ -330,7 +334,8 @@ cdef class Doc:
if annot is not heads and annot is not sent_starts and annot is not ent_iobs:
values.extend(annot)
for value in values:
self.vocab.strings.add(value)
if value is not None:
self.vocab.strings.add(value)
# if there are any other annotations, set them
if headings:
@ -1533,7 +1538,7 @@ cdef int set_children_from_heads(TokenC* tokens, int start, int end) except -1:
for i in range(start, end):
tokens[i].sent_start = -1
for i in range(start, end):
if tokens[i].head == 0:
if tokens[i].head == 0 and not Token.missing_head(&tokens[i]):
tokens[tokens[i].l_edge].sent_start = 1

View File

@ -9,6 +9,7 @@ from ..lexeme cimport Lexeme
from ..errors import Errors
cdef int MISSING_DEP = 0
cdef class Token:
cdef readonly Vocab vocab
@ -94,3 +95,13 @@ cdef class Token:
token.ent_kb_id = value
elif feat_name == SENT_START:
token.sent_start = value
@staticmethod
cdef inline int missing_dep(const TokenC* token) nogil:
return token.dep == MISSING_DEP
@staticmethod
cdef inline int missing_head(const TokenC* token) nogil:
return Token.missing_dep(token)

View File

@ -638,14 +638,26 @@ cdef class Token:
return False
return any(ancestor.i == self.i for ancestor in descendant.ancestors)
def has_head(self):
"""Check whether the token has annotated head information.
Return False when the head annotation is unset/missing.
RETURNS (bool): Whether the head annotation is valid or not.
"""
return not Token.missing_head(self.c)
property head:
"""The syntactic parent, or "governor", of this token.
"""The syntactic parent, or "governor", of this token.
If token.has_head() is `False`, this method will return itself.
RETURNS (Token): The token predicted by the parser to be the head of
the current token.
"""
def __get__(self):
return self.doc[self.i + self.c.head]
if not self.has_head():
return self
else:
return self.doc[self.i + self.c.head]
def __set__(self, Token new_head):
# This function sets the head of self to new_head and updates the
@ -858,6 +870,14 @@ cdef class Token:
def __set__(self, tag):
self.tag = self.vocab.strings.add(tag)
def has_dep(self):
"""Check whether the token has annotated dep information.
Returns False when the dep label is unset/missing.
RETURNS (bool): Whether the dep label is valid or not.
"""
return not Token.missing_dep(self.c)
property dep_:
"""RETURNS (str): The syntactic dependency label."""
def __get__(self):

View File

@ -12,6 +12,7 @@ from .iob_utils import biluo_to_iob, offsets_to_biluo_tags, doc_to_biluo_tags
from .iob_utils import biluo_tags_to_spans
from ..errors import Errors, Warnings
from ..pipeline._parser_internals import nonproj
from ..tokens.token cimport MISSING_DEP
from ..util import logger
@ -179,10 +180,15 @@ cdef class Example:
gold_to_cand = self.alignment.y2x
aligned_heads = [None] * self.x.length
aligned_deps = [None] * self.x.length
has_deps = [token.has_dep() for token in self.y]
has_heads = [token.has_head() for token in self.y]
heads = [token.head.i for token in self.y]
deps = [token.dep_ for token in self.y]
if projectivize:
heads, deps = nonproj.projectivize(heads, deps)
proj_heads, proj_deps = nonproj.projectivize(heads, deps)
# ensure that missing data remains missing
heads = [h if has_heads[i] else heads[i] for i, h in enumerate(proj_heads)]
deps = [d if has_deps[i] else deps[i] for i, d in enumerate(proj_deps)]
for cand_i in range(self.x.length):
if cand_to_gold.lengths[cand_i] == 1:
gold_i = cand_to_gold[cand_i].dataXd[0, 0]
@ -329,7 +335,10 @@ def _annot2array(vocab, tok_annot, doc_annot):
pass
elif key == "HEAD":
attrs.append(key)
values.append([h-i for i, h in enumerate(value)])
values.append([h-i if h is not None else 0 for i, h in enumerate(value)])
elif key == "DEP":
attrs.append(key)
values.append([vocab.strings.add(h) if h is not None else MISSING_DEP for h in value])
elif key == "SENT_START":
attrs.append(key)
values.append(value)