mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-09 16:58:17 +03:00
Merge branch 'master' into spacy.io
This commit is contained in:
Ines Montani
commit
efd1c9d9f5
BIN
.github/contributors/Schibsted.png
vendored
Normal file
BIN
.github/contributors/Schibsted.png
vendored
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 259 KiB |
|
|
@ -16,9 +16,9 @@ class KerasSimilarityShim(object):
|
|||
if get_features is None:
|
||||
get_features = get_word_ids
|
||||
|
||||
with (path / 'config.json').open() as file_:
|
||||
with (path / "config.json").open() as file_:
|
||||
model = model_from_json(file_.read())
|
||||
with (path / 'model').open('rb') as file_:
|
||||
with (path / "model").open("rb") as file_:
|
||||
weights = pickle.load(file_)
|
||||
|
||||
embeddings = get_embeddings(nlp.vocab)
|
||||
|
|
@ -33,8 +33,8 @@ class KerasSimilarityShim(object):
|
|||
self.max_length = max_length
|
||||
|
||||
def __call__(self, doc):
|
||||
doc.user_hooks['similarity'] = self.predict
|
||||
doc.user_span_hooks['similarity'] = self.predict
|
||||
doc.user_hooks["similarity"] = self.predict
|
||||
doc.user_span_hooks["similarity"] = self.predict
|
||||
|
||||
return doc
|
||||
|
||||
|
|
@ -54,8 +54,8 @@ def get_embeddings(vocab, nr_unk=100):
|
|||
oov = np.random.normal(size=(nr_unk, vocab.vectors_length))
|
||||
oov = oov / oov.sum(axis=1, keepdims=True)
|
||||
|
||||
vectors = np.zeros((num_vectors + nr_unk, vocab.vectors_length), dtype='float32')
|
||||
vectors[1:(nr_unk + 1), ] = oov
|
||||
vectors = np.zeros((num_vectors + nr_unk, vocab.vectors_length), dtype="float32")
|
||||
vectors[1 : (nr_unk + 1),] = oov
|
||||
for lex in vocab:
|
||||
if lex.has_vector and lex.vector_norm > 0:
|
||||
vectors[nr_unk + lex.rank + 1] = lex.vector / lex.vector_norm
|
||||
|
|
@ -64,7 +64,7 @@ def get_embeddings(vocab, nr_unk=100):
|
|||
|
||||
|
||||
def get_word_ids(docs, max_length=100, nr_unk=100):
|
||||
Xs = np.zeros((len(docs), max_length), dtype='int32')
|
||||
Xs = np.zeros((len(docs), max_length), dtype="int32")
|
||||
|
||||
for i, doc in enumerate(docs):
|
||||
for j, token in enumerate(doc):
|
||||
|
|
|
|||
7
examples/training/ner_example_data/README.md
Normal file
7
examples/training/ner_example_data/README.md
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
## Examples of NER/IOB data that can be converted with `spacy convert`
|
||||
|
||||
spacy JSON training files were generated with:
|
||||
|
||||
```
|
||||
python -m spacy convert -c iob -s -n 10 -b en file.iob
|
||||
```
|
||||
2
examples/training/ner_example_data/ner-sent-per-line.iob
Normal file
2
examples/training/ner_example_data/ner-sent-per-line.iob
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
When|WRB|O Sebastian|NNP|B-PERSON Thrun|NNP|I-PERSON started|VBD|O working|VBG|O on|IN|O self|NN|O -|HYPH|O driving|VBG|O cars|NNS|O at|IN|O Google|NNP|B-ORG in|IN|O 2007|CD|B-DATE ,|,|O few|JJ|O people|NNS|O outside|RB|O of|IN|O the|DT|O company|NN|O took|VBD|O him|PRP|O seriously|RB|O .|.|O
|
||||
“|''|O I|PRP|O can|MD|O tell|VB|O you|PRP|O very|RB|O senior|JJ|O CEOs|NNS|O of|IN|O major|JJ|O American|JJ|B-NORP car|NN|O companies|NNS|O would|MD|O shake|VB|O my|PRP$|O hand|NN|O and|CC|O turn|VB|O away|RB|O because|IN|O I|PRP|O was|VBD|O n’t|RB|O worth|JJ|O talking|VBG|O to|IN|O ,|,|O ”|''|O said|VBD|O Thrun|NNP|B-PERSON ,|,|O in|IN|O an|DT|O interview|NN|O with|IN|O Recode|NNP|B-ORG earlier|RBR|B-DATE this|DT|I-DATE week|NN|I-DATE .|.|O
|
||||
349
examples/training/ner_example_data/ner-sent-per-line.json
Normal file
349
examples/training/ner_example_data/ner-sent-per-line.json
Normal file
|
|
@ -0,0 +1,349 @@
|
|||
[
|
||||
{
|
||||
"id":0,
|
||||
"paragraphs":[
|
||||
{
|
||||
"sentences":[
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"When",
|
||||
"tag":"WRB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Sebastian",
|
||||
"tag":"NNP",
|
||||
"ner":"B-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"L-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"started",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"working",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"on",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"self",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"-",
|
||||
"tag":"HYPH",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"driving",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"cars",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"at",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Google",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"2007",
|
||||
"tag":"CD",
|
||||
"ner":"U-DATE"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"few",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"people",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"outside",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"the",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"company",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"took",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"him",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"seriously",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"\u201c",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"can",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"tell",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"you",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"very",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"senior",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"CEOs",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"major",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"American",
|
||||
"tag":"JJ",
|
||||
"ner":"U-NORP"
|
||||
},
|
||||
{
|
||||
"orth":"car",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"companies",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"would",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"shake",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"my",
|
||||
"tag":"PRP$",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"hand",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"and",
|
||||
"tag":"CC",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"turn",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"away",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"because",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"was",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"n\u2019t",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"worth",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"talking",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"to",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"\u201d",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"said",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"U-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"an",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"interview",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"with",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Recode",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"earlier",
|
||||
"tag":"RBR",
|
||||
"ner":"B-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"this",
|
||||
"tag":"DT",
|
||||
"ner":"I-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"week",
|
||||
"tag":"NN",
|
||||
"ner":"L-DATE"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
|
@ -0,0 +1,70 @@
|
|||
-DOCSTART- -X- O O
|
||||
|
||||
When WRB _ O
|
||||
Sebastian NNP _ B-PERSON
|
||||
Thrun NNP _ I-PERSON
|
||||
started VBD _ O
|
||||
working VBG _ O
|
||||
on IN _ O
|
||||
self NN _ O
|
||||
- HYPH _ O
|
||||
driving VBG _ O
|
||||
cars NNS _ O
|
||||
at IN _ O
|
||||
Google NNP _ B-ORG
|
||||
in IN _ O
|
||||
2007 CD _ B-DATE
|
||||
, , _ O
|
||||
few JJ _ O
|
||||
people NNS _ O
|
||||
outside RB _ O
|
||||
of IN _ O
|
||||
the DT _ O
|
||||
company NN _ O
|
||||
took VBD _ O
|
||||
him PRP _ O
|
||||
seriously RB _ O
|
||||
. . _ O
|
||||
|
||||
“ '' _ O
|
||||
I PRP _ O
|
||||
can MD _ O
|
||||
tell VB _ O
|
||||
you PRP _ O
|
||||
very RB _ O
|
||||
senior JJ _ O
|
||||
CEOs NNS _ O
|
||||
of IN _ O
|
||||
major JJ _ O
|
||||
American JJ _ B-NORP
|
||||
car NN _ O
|
||||
companies NNS _ O
|
||||
would MD _ O
|
||||
shake VB _ O
|
||||
my PRP$ _ O
|
||||
hand NN _ O
|
||||
and CC _ O
|
||||
turn VB _ O
|
||||
away RB _ O
|
||||
because IN _ O
|
||||
I PRP _ O
|
||||
was VBD _ O
|
||||
n’t RB _ O
|
||||
worth JJ _ O
|
||||
talking VBG _ O
|
||||
to IN _ O
|
||||
, , _ O
|
||||
” '' _ O
|
||||
said VBD _ O
|
||||
Thrun NNP _ B-PERSON
|
||||
, , _ O
|
||||
in IN _ O
|
||||
an DT _ O
|
||||
interview NN _ O
|
||||
with IN _ O
|
||||
Recode NNP _ B-ORG
|
||||
earlier RBR _ B-DATE
|
||||
this DT _ I-DATE
|
||||
week NN _ I-DATE
|
||||
. . _ O
|
||||
|
||||
|
|
@ -0,0 +1,349 @@
|
|||
[
|
||||
{
|
||||
"id":0,
|
||||
"paragraphs":[
|
||||
{
|
||||
"sentences":[
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"When",
|
||||
"tag":"WRB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Sebastian",
|
||||
"tag":"NNP",
|
||||
"ner":"B-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"L-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"started",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"working",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"on",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"self",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"-",
|
||||
"tag":"HYPH",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"driving",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"cars",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"at",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Google",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"2007",
|
||||
"tag":"CD",
|
||||
"ner":"U-DATE"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"few",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"people",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"outside",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"the",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"company",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"took",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"him",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"seriously",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"\u201c",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"can",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"tell",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"you",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"very",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"senior",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"CEOs",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"major",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"American",
|
||||
"tag":"JJ",
|
||||
"ner":"U-NORP"
|
||||
},
|
||||
{
|
||||
"orth":"car",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"companies",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"would",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"shake",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"my",
|
||||
"tag":"PRP$",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"hand",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"and",
|
||||
"tag":"CC",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"turn",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"away",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"because",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"was",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"n\u2019t",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"worth",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"talking",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"to",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"\u201d",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"said",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"U-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"an",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"interview",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"with",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Recode",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"earlier",
|
||||
"tag":"RBR",
|
||||
"ner":"B-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"this",
|
||||
"tag":"DT",
|
||||
"ner":"I-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"week",
|
||||
"tag":"NN",
|
||||
"ner":"L-DATE"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
|
@ -0,0 +1,66 @@
|
|||
When WRB O
|
||||
Sebastian NNP B-PERSON
|
||||
Thrun NNP I-PERSON
|
||||
started VBD O
|
||||
working VBG O
|
||||
on IN O
|
||||
self NN O
|
||||
- HYPH O
|
||||
driving VBG O
|
||||
cars NNS O
|
||||
at IN O
|
||||
Google NNP B-ORG
|
||||
in IN O
|
||||
2007 CD B-DATE
|
||||
, , O
|
||||
few JJ O
|
||||
people NNS O
|
||||
outside RB O
|
||||
of IN O
|
||||
the DT O
|
||||
company NN O
|
||||
took VBD O
|
||||
him PRP O
|
||||
seriously RB O
|
||||
. . O
|
||||
“ '' O
|
||||
I PRP O
|
||||
can MD O
|
||||
tell VB O
|
||||
you PRP O
|
||||
very RB O
|
||||
senior JJ O
|
||||
CEOs NNS O
|
||||
of IN O
|
||||
major JJ O
|
||||
American JJ B-NORP
|
||||
car NN O
|
||||
companies NNS O
|
||||
would MD O
|
||||
shake VB O
|
||||
my PRP$ O
|
||||
hand NN O
|
||||
and CC O
|
||||
turn VB O
|
||||
away RB O
|
||||
because IN O
|
||||
I PRP O
|
||||
was VBD O
|
||||
n’t RB O
|
||||
worth JJ O
|
||||
talking VBG O
|
||||
to IN O
|
||||
, , O
|
||||
” '' O
|
||||
said VBD O
|
||||
Thrun NNP B-PERSON
|
||||
, , O
|
||||
in IN O
|
||||
an DT O
|
||||
interview NN O
|
||||
with IN O
|
||||
Recode NNP B-ORG
|
||||
earlier RBR B-DATE
|
||||
this DT I-DATE
|
||||
week NN I-DATE
|
||||
. . O
|
||||
|
|
@ -0,0 +1,353 @@
|
|||
[
|
||||
{
|
||||
"id":0,
|
||||
"paragraphs":[
|
||||
{
|
||||
"sentences":[
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"When",
|
||||
"tag":"WRB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Sebastian",
|
||||
"tag":"NNP",
|
||||
"ner":"B-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"L-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"started",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"working",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"on",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"self",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"-",
|
||||
"tag":"HYPH",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"driving",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"cars",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"at",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Google",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"2007",
|
||||
"tag":"CD",
|
||||
"ner":"U-DATE"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"few",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"people",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"outside",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"the",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"company",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"took",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"him",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"seriously",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"\u201c",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"can",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"tell",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"you",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"very",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"senior",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"CEOs",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"major",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"American",
|
||||
"tag":"JJ",
|
||||
"ner":"U-NORP"
|
||||
},
|
||||
{
|
||||
"orth":"car",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"companies",
|
||||
"tag":"NNS",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"would",
|
||||
"tag":"MD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"shake",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"my",
|
||||
"tag":"PRP$",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"hand",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"and",
|
||||
"tag":"CC",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"turn",
|
||||
"tag":"VB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"away",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"because",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"PRP",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"was",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"n\u2019t",
|
||||
"tag":"RB",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"worth",
|
||||
"tag":"JJ",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"talking",
|
||||
"tag":"VBG",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"to",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"\u201d",
|
||||
"tag":"''",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"said",
|
||||
"tag":"VBD",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"NNP",
|
||||
"ner":"U-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":",",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"an",
|
||||
"tag":"DT",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"interview",
|
||||
"tag":"NN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"with",
|
||||
"tag":"IN",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Recode",
|
||||
"tag":"NNP",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"earlier",
|
||||
"tag":"RBR",
|
||||
"ner":"B-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"this",
|
||||
"tag":"DT",
|
||||
"ner":"I-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"week",
|
||||
"tag":"NN",
|
||||
"ner":"L-DATE"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":".",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
66
examples/training/ner_example_data/ner-token-per-line.iob
Normal file
66
examples/training/ner_example_data/ner-token-per-line.iob
Normal file
|
|
@ -0,0 +1,66 @@
|
|||
When O
|
||||
Sebastian B-PERSON
|
||||
Thrun I-PERSON
|
||||
started O
|
||||
working O
|
||||
on O
|
||||
self O
|
||||
- O
|
||||
driving O
|
||||
cars O
|
||||
at O
|
||||
Google B-ORG
|
||||
in O
|
||||
2007 B-DATE
|
||||
, O
|
||||
few O
|
||||
people O
|
||||
outside O
|
||||
of O
|
||||
the O
|
||||
company O
|
||||
took O
|
||||
him O
|
||||
seriously O
|
||||
. O
|
||||
“ O
|
||||
I O
|
||||
can O
|
||||
tell O
|
||||
you O
|
||||
very O
|
||||
senior O
|
||||
CEOs O
|
||||
of O
|
||||
major O
|
||||
American B-NORP
|
||||
car O
|
||||
companies O
|
||||
would O
|
||||
shake O
|
||||
my O
|
||||
hand O
|
||||
and O
|
||||
turn O
|
||||
away O
|
||||
because O
|
||||
I O
|
||||
was O
|
||||
n’t O
|
||||
worth O
|
||||
talking O
|
||||
to O
|
||||
, O
|
||||
” O
|
||||
said O
|
||||
Thrun B-PERSON
|
||||
, O
|
||||
in O
|
||||
an O
|
||||
interview O
|
||||
with O
|
||||
Recode B-ORG
|
||||
earlier B-DATE
|
||||
this I-DATE
|
||||
week I-DATE
|
||||
. O
|
||||
353
examples/training/ner_example_data/ner-token-per-line.json
Normal file
353
examples/training/ner_example_data/ner-token-per-line.json
Normal file
|
|
@ -0,0 +1,353 @@
|
|||
[
|
||||
{
|
||||
"id":0,
|
||||
"paragraphs":[
|
||||
{
|
||||
"sentences":[
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"When",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Sebastian",
|
||||
"tag":"-",
|
||||
"ner":"B-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"-",
|
||||
"ner":"L-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":"started",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"working",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"on",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"self",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"-",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"driving",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"cars",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"at",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Google",
|
||||
"tag":"-",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"2007",
|
||||
"tag":"-",
|
||||
"ner":"U-DATE"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"few",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"people",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"outside",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"the",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"company",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"took",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"him",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"seriously",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"\u201c",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tokens":[
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"can",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"tell",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"you",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"very",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"senior",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"CEOs",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"of",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"major",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"American",
|
||||
"tag":"-",
|
||||
"ner":"U-NORP"
|
||||
},
|
||||
{
|
||||
"orth":"car",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"companies",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"would",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"shake",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"my",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"hand",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"and",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"turn",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"away",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"because",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"I",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"was",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"n\u2019t",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"worth",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"talking",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"to",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"\u201d",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"said",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Thrun",
|
||||
"tag":"-",
|
||||
"ner":"U-PERSON"
|
||||
},
|
||||
{
|
||||
"orth":",",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"in",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"an",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"interview",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"with",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
},
|
||||
{
|
||||
"orth":"Recode",
|
||||
"tag":"-",
|
||||
"ner":"U-ORG"
|
||||
},
|
||||
{
|
||||
"orth":"earlier",
|
||||
"tag":"-",
|
||||
"ner":"B-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"this",
|
||||
"tag":"-",
|
||||
"ner":"I-DATE"
|
||||
},
|
||||
{
|
||||
"orth":"week",
|
||||
"tag":"-",
|
||||
"ner":"L-DATE"
|
||||
},
|
||||
{
|
||||
"orth":".",
|
||||
"tag":"-",
|
||||
"ner":"O"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
|
@ -80,7 +80,7 @@ def main(model_name, unlabelled_loc):
|
|||
nlp.rehearse(raw_batch, sgd=optimizer, losses=r_losses)
|
||||
print("Losses", losses)
|
||||
print("R. Losses", r_losses)
|
||||
print(nlp.get_pipe('ner').model.unseen_classes)
|
||||
print(nlp.get_pipe("ner").model.unseen_classes)
|
||||
test_text = "Do you like horses?"
|
||||
doc = nlp(test_text)
|
||||
print("Entities in '%s'" % test_text)
|
||||
|
|
@ -88,7 +88,5 @@ def main(model_name, unlabelled_loc):
|
|||
print(ent.label_, ent.text)
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
plac.call(main)
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ from spacy.util import minibatch, compounding
|
|||
output_dir=("Optional output directory", "option", "o", Path),
|
||||
n_texts=("Number of texts to train from", "option", "t", int),
|
||||
n_iter=("Number of training iterations", "option", "n", int),
|
||||
init_tok2vec=("Pretrained tok2vec weights", "option", "t2v", Path)
|
||||
init_tok2vec=("Pretrained tok2vec weights", "option", "t2v", Path),
|
||||
)
|
||||
def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None):
|
||||
if output_dir is not None:
|
||||
|
|
@ -43,11 +43,7 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None
|
|||
# nlp.create_pipe works for built-ins that are registered with spaCy
|
||||
if "textcat" not in nlp.pipe_names:
|
||||
textcat = nlp.create_pipe(
|
||||
"textcat",
|
||||
config={
|
||||
"exclusive_classes": True,
|
||||
"architecture": "simple_cnn",
|
||||
}
|
||||
"textcat", config={"exclusive_classes": True, "architecture": "simple_cnn"}
|
||||
)
|
||||
nlp.add_pipe(textcat, last=True)
|
||||
# otherwise, get it, so we can add labels to it
|
||||
|
|
|
|||
|
|
@ -5,12 +5,14 @@ import plac
|
|||
from pathlib import Path
|
||||
from wasabi import Printer
|
||||
import srsly
|
||||
import re
|
||||
|
||||
from .converters import conllu2json, iob2json, conll_ner2json
|
||||
from .converters import ner_jsonl2json
|
||||
|
||||
|
||||
# Converters are matched by file extension. To add a converter, add a new
|
||||
# Converters are matched by file extension except for ner/iob, which are
|
||||
# matched by file extension and content. To add a converter, add a new
|
||||
# entry to this dict with the file extension mapped to the converter function
|
||||
# imported from /converters.
|
||||
CONVERTERS = {
|
||||
|
|
@ -31,7 +33,9 @@ FILE_TYPES_STDOUT = ("json", "jsonl")
|
|||
input_file=("Input file", "positional", None, str),
|
||||
output_dir=("Output directory. '-' for stdout.", "positional", None, str),
|
||||
file_type=("Type of data to produce: {}".format(FILE_TYPES), "option", "t", str),
|
||||
n_sents=("Number of sentences per doc", "option", "n", int),
|
||||
n_sents=("Number of sentences per doc (0 to disable)", "option", "n", int),
|
||||
seg_sents=("Segment sentences (for -c ner)", "flag", "s"),
|
||||
model=("Model for sentence segmentation (for -s)", "option", "b", str),
|
||||
converter=("Converter: {}".format(tuple(CONVERTERS.keys())), "option", "c", str),
|
||||
lang=("Language (if tokenizer required)", "option", "l", str),
|
||||
morphology=("Enable appending morphology to tags", "flag", "m", bool),
|
||||
|
|
@ -41,6 +45,8 @@ def convert(
|
|||
output_dir="-",
|
||||
file_type="json",
|
||||
n_sents=1,
|
||||
seg_sents=False,
|
||||
model=None,
|
||||
morphology=False,
|
||||
converter="auto",
|
||||
lang=None,
|
||||
|
|
@ -70,14 +76,33 @@ def convert(
|
|||
msg.fail("Input file not found", input_path, exits=1)
|
||||
if output_dir != "-" and not Path(output_dir).exists():
|
||||
msg.fail("Output directory not found", output_dir, exits=1)
|
||||
input_data = input_path.open("r", encoding="utf-8").read()
|
||||
if converter == "auto":
|
||||
converter = input_path.suffix[1:]
|
||||
if converter == "ner" or converter == "iob":
|
||||
converter_autodetect = autodetect_ner_format(input_data)
|
||||
if converter_autodetect == "ner":
|
||||
msg.info("Auto-detected token-per-line NER format")
|
||||
converter = converter_autodetect
|
||||
elif converter_autodetect == "iob":
|
||||
msg.info("Auto-detected sentence-per-line NER format")
|
||||
converter = converter_autodetect
|
||||
else:
|
||||
msg.warn(
|
||||
"Can't automatically detect NER format. Conversion may not succeed. See https://spacy.io/api/cli#convert"
|
||||
)
|
||||
if converter not in CONVERTERS:
|
||||
msg.fail("Can't find converter for {}".format(converter), exits=1)
|
||||
# Use converter function to convert data
|
||||
func = CONVERTERS[converter]
|
||||
input_data = input_path.open("r", encoding="utf-8").read()
|
||||
data = func(input_data, n_sents=n_sents, use_morphology=morphology, lang=lang)
|
||||
data = func(
|
||||
input_data,
|
||||
n_sents=n_sents,
|
||||
seg_sents=seg_sents,
|
||||
use_morphology=morphology,
|
||||
lang=lang,
|
||||
model=model,
|
||||
)
|
||||
if output_dir != "-":
|
||||
# Export data to a file
|
||||
suffix = ".{}".format(file_type)
|
||||
|
|
@ -88,10 +113,31 @@ def convert(
|
|||
srsly.write_jsonl(output_file, data)
|
||||
elif file_type == "msg":
|
||||
srsly.write_msgpack(output_file, data)
|
||||
msg.good("Generated output file ({} documents)".format(len(data)), output_file)
|
||||
msg.good(
|
||||
"Generated output file ({} documents): {}".format(len(data), output_file)
|
||||
)
|
||||
else:
|
||||
# Print to stdout
|
||||
if file_type == "json":
|
||||
srsly.write_json("-", data)
|
||||
elif file_type == "jsonl":
|
||||
srsly.write_jsonl("-", data)
|
||||
|
||||
|
||||
def autodetect_ner_format(input_data):
|
||||
# guess format from the first 20 lines
|
||||
lines = input_data.split("\n")[:20]
|
||||
format_guesses = {"ner": 0, "iob": 0}
|
||||
iob_re = re.compile(r"\S+\|(O|[IB]-\S+)")
|
||||
ner_re = re.compile(r"\S+\s+(O|[IB]-\S+)$")
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if iob_re.search(line):
|
||||
format_guesses["iob"] += 1
|
||||
if ner_re.search(line):
|
||||
format_guesses["ner"] += 1
|
||||
if format_guesses["iob"] == 0 and format_guesses["ner"] > 0:
|
||||
return "ner"
|
||||
if format_guesses["ner"] == 0 and format_guesses["iob"] > 0:
|
||||
return "iob"
|
||||
return None
|
||||
|
|
|
|||
|
|
@ -1,17 +1,89 @@
|
|||
# coding: utf8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from wasabi import Printer
|
||||
|
||||
from ...gold import iob_to_biluo
|
||||
from ...lang.xx import MultiLanguage
|
||||
from ...tokens.doc import Doc
|
||||
from ...util import load_model
|
||||
|
||||
|
||||
def conll_ner2json(input_data, **kwargs):
|
||||
def conll_ner2json(input_data, n_sents=10, seg_sents=False, model=None, **kwargs):
|
||||
"""
|
||||
Convert files in the CoNLL-2003 NER format into JSON format for use with
|
||||
train cli.
|
||||
Convert files in the CoNLL-2003 NER format and similar
|
||||
whitespace-separated columns into JSON format for use with train cli.
|
||||
|
||||
The first column is the tokens, the final column is the IOB tags. If an
|
||||
additional second column is present, the second column is the tags.
|
||||
|
||||
Sentences are separated with whitespace and documents can be separated
|
||||
using the line "-DOCSTART- -X- O O".
|
||||
|
||||
Sample format:
|
||||
|
||||
-DOCSTART- -X- O O
|
||||
|
||||
I O
|
||||
like O
|
||||
London B-GPE
|
||||
and O
|
||||
New B-GPE
|
||||
York I-GPE
|
||||
City I-GPE
|
||||
. O
|
||||
|
||||
"""
|
||||
delimit_docs = "-DOCSTART- -X- O O"
|
||||
msg = Printer()
|
||||
doc_delimiter = "-DOCSTART- -X- O O"
|
||||
# check for existing delimiters, which should be preserved
|
||||
if "\n\n" in input_data and seg_sents:
|
||||
msg.warn(
|
||||
"Sentence boundaries found, automatic sentence segmentation with "
|
||||
"`-s` disabled."
|
||||
)
|
||||
seg_sents = False
|
||||
if doc_delimiter in input_data and n_sents:
|
||||
msg.warn(
|
||||
"Document delimiters found, automatic document segmentation with "
|
||||
"`-n` disabled."
|
||||
)
|
||||
n_sents = 0
|
||||
# do document segmentation with existing sentences
|
||||
if "\n\n" in input_data and doc_delimiter not in input_data and n_sents:
|
||||
n_sents_info(msg, n_sents)
|
||||
input_data = segment_docs(input_data, n_sents, doc_delimiter)
|
||||
# do sentence segmentation with existing documents
|
||||
if "\n\n" not in input_data and doc_delimiter in input_data and seg_sents:
|
||||
input_data = segment_sents_and_docs(input_data, 0, "", model=model, msg=msg)
|
||||
# do both sentence segmentation and document segmentation according
|
||||
# to options
|
||||
if "\n\n" not in input_data and doc_delimiter not in input_data:
|
||||
# sentence segmentation required for document segmentation
|
||||
if n_sents > 0 and not seg_sents:
|
||||
msg.warn(
|
||||
"No sentence boundaries found to use with option `-n {}`. "
|
||||
"Use `-s` to automatically segment sentences or `-n 0` "
|
||||
"to disable.".format(n_sents)
|
||||
)
|
||||
else:
|
||||
n_sents_info(msg, n_sents)
|
||||
input_data = segment_sents_and_docs(
|
||||
input_data, n_sents, doc_delimiter, model=model, msg=msg
|
||||
)
|
||||
# provide warnings for problematic data
|
||||
if "\n\n" not in input_data:
|
||||
msg.warn(
|
||||
"No sentence boundaries found. Use `-s` to automatically segment "
|
||||
"sentences."
|
||||
)
|
||||
if doc_delimiter not in input_data:
|
||||
msg.warn(
|
||||
"No document delimiters found. Use `-n` to automatically group "
|
||||
"sentences into documents."
|
||||
)
|
||||
output_docs = []
|
||||
for doc in input_data.strip().split(delimit_docs):
|
||||
for doc in input_data.strip().split(doc_delimiter):
|
||||
doc = doc.strip()
|
||||
if not doc:
|
||||
continue
|
||||
|
|
@ -21,7 +93,19 @@ def conll_ner2json(input_data, **kwargs):
|
|||
if not sent:
|
||||
continue
|
||||
lines = [line.strip() for line in sent.split("\n") if line.strip()]
|
||||
words, tags, chunks, iob_ents = zip(*[line.split() for line in lines])
|
||||
cols = list(zip(*[line.split() for line in lines]))
|
||||
if len(cols) < 2:
|
||||
raise ValueError(
|
||||
"The token-per-line NER file is not formatted correctly. "
|
||||
"Try checking whitespace and delimiters. See "
|
||||
"https://spacy.io/api/cli#convert"
|
||||
)
|
||||
words = cols[0]
|
||||
iob_ents = cols[-1]
|
||||
if len(cols) > 2:
|
||||
tags = cols[1]
|
||||
else:
|
||||
tags = ["-"] * len(words)
|
||||
biluo_ents = iob_to_biluo(iob_ents)
|
||||
output_doc.append(
|
||||
{
|
||||
|
|
@ -36,3 +120,53 @@ def conll_ner2json(input_data, **kwargs):
|
|||
)
|
||||
output_doc = []
|
||||
return output_docs
|
||||
|
||||
|
||||
def segment_sents_and_docs(doc, n_sents, doc_delimiter, model=None, msg=None):
|
||||
sentencizer = None
|
||||
if model:
|
||||
nlp = load_model(model)
|
||||
if "parser" in nlp.pipe_names:
|
||||
msg.info("Segmenting sentences with parser from model '{}'.".format(model))
|
||||
sentencizer = nlp.get_pipe("parser")
|
||||
if not sentencizer:
|
||||
msg.info(
|
||||
"Segmenting sentences with sentencizer. (Use `-b model` for "
|
||||
"improved parser-based sentence segmentation.)"
|
||||
)
|
||||
nlp = MultiLanguage()
|
||||
sentencizer = nlp.create_pipe("sentencizer")
|
||||
lines = doc.strip().split("\n")
|
||||
words = [line.strip().split()[0] for line in lines]
|
||||
nlpdoc = Doc(nlp.vocab, words=words)
|
||||
sentencizer(nlpdoc)
|
||||
lines_with_segs = []
|
||||
sent_count = 0
|
||||
for i, token in enumerate(nlpdoc):
|
||||
if token.is_sent_start:
|
||||
if n_sents and sent_count % n_sents == 0:
|
||||
lines_with_segs.append(doc_delimiter)
|
||||
lines_with_segs.append("")
|
||||
sent_count += 1
|
||||
lines_with_segs.append(lines[i])
|
||||
return "\n".join(lines_with_segs)
|
||||
|
||||
|
||||
def segment_docs(input_data, n_sents, doc_delimiter):
|
||||
sent_delimiter = "\n\n"
|
||||
sents = input_data.split(sent_delimiter)
|
||||
docs = [sents[i : i + n_sents] for i in range(0, len(sents), n_sents)]
|
||||
input_data = ""
|
||||
for doc in docs:
|
||||
input_data += sent_delimiter + doc_delimiter
|
||||
input_data += sent_delimiter.join(doc)
|
||||
return input_data
|
||||
|
||||
|
||||
def n_sents_info(msg, n_sents):
|
||||
msg.info("Grouping every {} sentences into a document.".format(n_sents))
|
||||
if n_sents == 1:
|
||||
msg.warn(
|
||||
"To generate better training data, you may want to group "
|
||||
"sentences into documents with `-n 10`."
|
||||
)
|
||||
|
|
|
|||
|
|
@ -2,17 +2,30 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
from wasabi import Printer
|
||||
|
||||
from ...gold import iob_to_biluo
|
||||
from ...util import minibatch
|
||||
from .conll_ner2json import n_sents_info
|
||||
|
||||
|
||||
def iob2json(input_data, n_sents=10, *args, **kwargs):
|
||||
"""
|
||||
Convert IOB files into JSON format for use with train cli.
|
||||
Convert IOB files with one sentence per line and tags separated with '|'
|
||||
into JSON format for use with train cli. IOB and IOB2 are accepted.
|
||||
|
||||
Sample formats:
|
||||
|
||||
I|O like|O London|I-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O
|
||||
I|O like|O London|B-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O
|
||||
I|PRP|O like|VBP|O London|NNP|I-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O
|
||||
I|PRP|O like|VBP|O London|NNP|B-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O
|
||||
"""
|
||||
sentences = read_iob(input_data.split("\n"))
|
||||
docs = merge_sentences(sentences, n_sents)
|
||||
msg = Printer()
|
||||
docs = read_iob(input_data.split("\n"))
|
||||
if n_sents > 0:
|
||||
n_sents_info(msg, n_sents)
|
||||
docs = merge_sentences(docs, n_sents)
|
||||
return docs
|
||||
|
||||
|
||||
|
|
@ -21,7 +34,7 @@ def read_iob(raw_sents):
|
|||
for line in raw_sents:
|
||||
if not line.strip():
|
||||
continue
|
||||
tokens = [re.split("[^\w\-]", line.strip())]
|
||||
tokens = [t.split("|") for t in line.split()]
|
||||
if len(tokens[0]) == 3:
|
||||
words, pos, iob = zip(*tokens)
|
||||
elif len(tokens[0]) == 2:
|
||||
|
|
@ -29,7 +42,7 @@ def read_iob(raw_sents):
|
|||
pos = ["-"] * len(words)
|
||||
else:
|
||||
raise ValueError(
|
||||
"The iob/iob2 file is not formatted correctly. Try checking whitespace and delimiters."
|
||||
"The sentence-per-line IOB/IOB2 file is not formatted correctly. Try checking whitespace and delimiters. See https://spacy.io/api/cli#convert"
|
||||
)
|
||||
biluo = iob_to_biluo(iob)
|
||||
sentences.append(
|
||||
|
|
@ -40,7 +53,7 @@ def read_iob(raw_sents):
|
|||
)
|
||||
sentences = [{"tokens": sent} for sent in sentences]
|
||||
paragraphs = [{"sentences": [sent]} for sent in sentences]
|
||||
docs = [{"id": 0, "paragraphs": [para]} for para in paragraphs]
|
||||
docs = [{"id": i, "paragraphs": [para]} for i, para in enumerate(paragraphs)]
|
||||
return docs
|
||||
|
||||
|
||||
|
|
@ -50,7 +63,7 @@ def merge_sentences(docs, n_sents):
|
|||
group = list(group)
|
||||
first = group.pop(0)
|
||||
to_extend = first["paragraphs"][0]["sentences"]
|
||||
for sent in group[1:]:
|
||||
for sent in group:
|
||||
to_extend.extend(sent["paragraphs"][0]["sentences"])
|
||||
merged.append(first)
|
||||
return merged
|
||||
|
|
|
|||
|
|
@ -38,8 +38,8 @@ from . import about
|
|||
class BaseDefaults(object):
|
||||
@classmethod
|
||||
def create_lemmatizer(cls, nlp=None, lookups=None):
|
||||
lemma_rules, lemma_index, lemma_exc, lemma_lookup = util.get_lemma_tables(lookups)
|
||||
return Lemmatizer(lemma_index, lemma_exc, lemma_rules, lemma_lookup)
|
||||
rules, index, exc, lookup = util.get_lemma_tables(lookups)
|
||||
return Lemmatizer(index, exc, rules, lookup)
|
||||
|
||||
@classmethod
|
||||
def create_lookups(cls, nlp=None):
|
||||
|
|
|
|||
|
|
@ -142,10 +142,34 @@ TOKEN_PATTERN_SCHEMA = {
|
|||
"title": "Token is whitespace",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_BRACKET": {
|
||||
"title": "Token is a bracket",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_QUOTE": {
|
||||
"title": "Token is a quotation mark",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_LEFT_PUNCT": {
|
||||
"title": "Token is a left punctuation mark",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_RIGHT_PUNCT": {
|
||||
"title": "Token is a right punctuation mark",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_CURRENCY": {
|
||||
"title": "Token is a currency symbol",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_STOP": {
|
||||
"title": "Token is stop word",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"IS_SENT_START": {
|
||||
"title": "Token is the first in a sentence",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
},
|
||||
"LIKE_NUM": {
|
||||
"title": "Token resembles a number",
|
||||
"$ref": "#/definitions/boolean_value",
|
||||
|
|
|
|||
|
|
@ -258,7 +258,7 @@ cdef class Begin:
|
|||
@staticmethod
|
||||
cdef bint is_valid(const StateC* st, attr_t label) nogil:
|
||||
cdef int preset_ent_iob = st.B_(0).ent_iob
|
||||
cdef int preset_ent_label = st.B_(0).ent_type
|
||||
cdef attr_t preset_ent_label = st.B_(0).ent_type
|
||||
# If we're the last token of the input, we can't B -- must U or O.
|
||||
if st.B(1) == -1:
|
||||
return False
|
||||
|
|
@ -395,6 +395,9 @@ cdef class Last:
|
|||
return False
|
||||
elif not st.entity_is_open():
|
||||
return False
|
||||
elif st.B_(0).ent_iob == 1 and st.B_(1).ent_iob != 1:
|
||||
# If a preset entity has I followed by not-I, is L
|
||||
return True
|
||||
elif st.E_(0).ent_type != label:
|
||||
return False
|
||||
elif st.B_(1).ent_iob == 1:
|
||||
|
|
|
|||
|
|
@ -6,8 +6,13 @@ import pytest
|
|||
|
||||
@pytest.mark.parametrize(
|
||||
"text,norms,lemmas",
|
||||
[("о.г.", ["ове године"], ["ова година"]), ("чет.", ["четвртак"], ["четвртак"]),
|
||||
("гђа", ["госпођа"], ["госпођа"]), ("ил'", ["или"], ["или"])])
|
||||
[
|
||||
("о.г.", ["ове године"], ["ова година"]),
|
||||
("чет.", ["четвртак"], ["четвртак"]),
|
||||
("гђа", ["госпођа"], ["госпођа"]),
|
||||
("ил'", ["или"], ["или"]),
|
||||
],
|
||||
)
|
||||
def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
|
||||
tokens = sr_tokenizer(text)
|
||||
assert len(tokens) == 1
|
||||
|
|
|
|||
|
|
@ -380,3 +380,33 @@ def test_attr_pipeline_checks(en_vocab):
|
|||
matcher(doc1)
|
||||
matcher(doc2)
|
||||
matcher(doc3)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"pattern,text",
|
||||
[
|
||||
([{"IS_ALPHA": True}], "a"),
|
||||
([{"IS_ASCII": True}], "a"),
|
||||
([{"IS_DIGIT": True}], "1"),
|
||||
([{"IS_LOWER": True}], "a"),
|
||||
([{"IS_UPPER": True}], "A"),
|
||||
([{"IS_TITLE": True}], "Aaaa"),
|
||||
([{"IS_PUNCT": True}], "."),
|
||||
([{"IS_SPACE": True}], "\n"),
|
||||
([{"IS_BRACKET": True}], "["),
|
||||
([{"IS_QUOTE": True}], '"'),
|
||||
([{"IS_LEFT_PUNCT": True}], "``"),
|
||||
([{"IS_RIGHT_PUNCT": True}], "''"),
|
||||
([{"IS_STOP": True}], "the"),
|
||||
([{"LIKE_NUM": True}], "1"),
|
||||
([{"LIKE_URL": True}], "http://example.com"),
|
||||
([{"LIKE_EMAIL": True}], "mail@example.com"),
|
||||
],
|
||||
)
|
||||
def test_matcher_schema_token_attributes(en_vocab, pattern, text):
|
||||
matcher = Matcher(en_vocab)
|
||||
doc = Doc(en_vocab, words=text.split(" "))
|
||||
matcher.add("Rule", None, pattern)
|
||||
assert len(matcher) == 1
|
||||
matches = matcher(doc)
|
||||
assert len(matches) == 1
|
||||
|
|
|
|||
|
|
@ -329,3 +329,4 @@ def test_issue_1971_4(en_vocab):
|
|||
matches = matcher(doc)
|
||||
# Uncommenting this caused a segmentation fault
|
||||
assert len(matches) == 1
|
||||
assert matches[0] == (en_vocab.strings["TEST"], 0, 3)
|
||||
|
|
|
|||
57
spacy/tests/regression/test_issue4190.py
Normal file
57
spacy/tests/regression/test_issue4190.py
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
# coding: utf8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from spacy.lang.en import English
|
||||
|
||||
import spacy
|
||||
from spacy.tokenizer import Tokenizer
|
||||
|
||||
from spacy.tests.util import make_tempdir
|
||||
|
||||
|
||||
def test_issue4190():
|
||||
test_string = "Test c."
|
||||
|
||||
# Load default language
|
||||
nlp_1 = English()
|
||||
doc_1a = nlp_1(test_string)
|
||||
result_1a = [token.text for token in doc_1a]
|
||||
|
||||
# Modify tokenizer
|
||||
customize_tokenizer(nlp_1)
|
||||
doc_1b = nlp_1(test_string)
|
||||
result_1b = [token.text for token in doc_1b]
|
||||
|
||||
# Save and Reload
|
||||
with make_tempdir() as model_dir:
|
||||
nlp_1.to_disk(model_dir)
|
||||
nlp_2 = spacy.load(model_dir)
|
||||
|
||||
# This should be the modified tokenizer
|
||||
doc_2 = nlp_2(test_string)
|
||||
result_2 = [token.text for token in doc_2]
|
||||
|
||||
assert result_1b == result_2
|
||||
|
||||
|
||||
def customize_tokenizer(nlp):
|
||||
prefix_re = spacy.util.compile_prefix_regex(nlp.Defaults.prefixes)
|
||||
suffix_re = spacy.util.compile_suffix_regex(nlp.Defaults.suffixes)
|
||||
infix_re = spacy.util.compile_infix_regex(nlp.Defaults.infixes)
|
||||
|
||||
# remove all exceptions where a single letter is followed by a period (e.g. 'h.')
|
||||
exceptions = {
|
||||
k: v
|
||||
for k, v in dict(nlp.Defaults.tokenizer_exceptions).items()
|
||||
if not (len(k) == 2 and k[1] == ".")
|
||||
}
|
||||
new_tokenizer = Tokenizer(
|
||||
nlp.vocab,
|
||||
exceptions,
|
||||
prefix_search=prefix_re.search,
|
||||
suffix_search=suffix_re.search,
|
||||
infix_finditer=infix_re.finditer,
|
||||
token_match=nlp.tokenizer.token_match,
|
||||
)
|
||||
|
||||
nlp.tokenizer = new_tokenizer
|
||||
|
|
@ -4,7 +4,7 @@ from __future__ import unicode_literals
|
|||
import pytest
|
||||
|
||||
from spacy.lang.en import English
|
||||
from spacy.cli.converters import conllu2json
|
||||
from spacy.cli.converters import conllu2json, iob2json, conll_ner2json
|
||||
from spacy.cli.pretrain import make_docs
|
||||
|
||||
|
||||
|
|
@ -32,6 +32,95 @@ def test_cli_converters_conllu2json():
|
|||
assert [t["ner"] for t in tokens] == ["O", "B-PER", "L-PER", "O"]
|
||||
|
||||
|
||||
def test_cli_converters_iob2json():
|
||||
lines = [
|
||||
"I|O like|O London|I-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
|
||||
"I|O like|O London|B-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
|
||||
"I|PRP|O like|VBP|O London|NNP|I-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
|
||||
"I|PRP|O like|VBP|O London|NNP|B-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
|
||||
]
|
||||
input_data = "\n".join(lines)
|
||||
converted = iob2json(input_data, n_sents=10)
|
||||
assert len(converted) == 1
|
||||
assert converted[0]["id"] == 0
|
||||
assert len(converted[0]["paragraphs"]) == 1
|
||||
assert len(converted[0]["paragraphs"][0]["sentences"]) == 4
|
||||
for i in range(0, 4):
|
||||
sent = converted[0]["paragraphs"][0]["sentences"][i]
|
||||
assert len(sent["tokens"]) == 8
|
||||
tokens = sent["tokens"]
|
||||
# fmt: off
|
||||
assert [t["orth"] for t in tokens] == ["I", "like", "London", "and", "New", "York", "City", "."]
|
||||
assert [t["ner"] for t in tokens] == ["O", "O", "U-GPE", "O", "B-GPE", "I-GPE", "L-GPE", "O"]
|
||||
# fmt: on
|
||||
|
||||
|
||||
def test_cli_converters_conll_ner2json():
|
||||
lines = [
|
||||
"-DOCSTART- -X- O O",
|
||||
"",
|
||||
"I\tO",
|
||||
"like\tO",
|
||||
"London\tB-GPE",
|
||||
"and\tO",
|
||||
"New\tB-GPE",
|
||||
"York\tI-GPE",
|
||||
"City\tI-GPE",
|
||||
".\tO",
|
||||
"",
|
||||
"I O",
|
||||
"like O",
|
||||
"London B-GPE",
|
||||
"and O",
|
||||
"New B-GPE",
|
||||
"York I-GPE",
|
||||
"City I-GPE",
|
||||
". O",
|
||||
"",
|
||||
"I PRP O",
|
||||
"like VBP O",
|
||||
"London NNP B-GPE",
|
||||
"and CC O",
|
||||
"New NNP B-GPE",
|
||||
"York NNP I-GPE",
|
||||
"City NNP I-GPE",
|
||||
". . O",
|
||||
"",
|
||||
"I PRP _ O",
|
||||
"like VBP _ O",
|
||||
"London NNP _ B-GPE",
|
||||
"and CC _ O",
|
||||
"New NNP _ B-GPE",
|
||||
"York NNP _ I-GPE",
|
||||
"City NNP _ I-GPE",
|
||||
". . _ O",
|
||||
"",
|
||||
"I\tPRP\t_\tO",
|
||||
"like\tVBP\t_\tO",
|
||||
"London\tNNP\t_\tB-GPE",
|
||||
"and\tCC\t_\tO",
|
||||
"New\tNNP\t_\tB-GPE",
|
||||
"York\tNNP\t_\tI-GPE",
|
||||
"City\tNNP\t_\tI-GPE",
|
||||
".\t.\t_\tO",
|
||||
]
|
||||
input_data = "\n".join(lines)
|
||||
converted = conll_ner2json(input_data, n_sents=10)
|
||||
print(converted)
|
||||
assert len(converted) == 1
|
||||
assert converted[0]["id"] == 0
|
||||
assert len(converted[0]["paragraphs"]) == 1
|
||||
assert len(converted[0]["paragraphs"][0]["sentences"]) == 5
|
||||
for i in range(0, 5):
|
||||
sent = converted[0]["paragraphs"][0]["sentences"][i]
|
||||
assert len(sent["tokens"]) == 8
|
||||
tokens = sent["tokens"]
|
||||
# fmt: off
|
||||
assert [t["orth"] for t in tokens] == ["I", "like", "London", "and", "New", "York", "City", "."]
|
||||
assert [t["ner"] for t in tokens] == ["O", "O", "U-GPE", "O", "B-GPE", "I-GPE", "L-GPE", "O"]
|
||||
# fmt: on
|
||||
|
||||
|
||||
def test_pretrain_make_docs():
|
||||
nlp = English()
|
||||
|
||||
|
|
|
|||
|
|
@ -441,8 +441,13 @@ cdef class Tokenizer:
|
|||
self.infix_finditer = re.compile(data["infix_finditer"]).finditer
|
||||
if data.get("token_match"):
|
||||
self.token_match = re.compile(data["token_match"]).match
|
||||
if data.get("rules"):
|
||||
# make sure to hard reset the cache to remove data from the default exceptions
|
||||
self._rules = {}
|
||||
self._cache = PreshMap()
|
||||
for string, substrings in data.get("rules", {}).items():
|
||||
self.add_special_case(string, substrings)
|
||||
|
||||
return self
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -145,6 +145,8 @@ $ python -m spacy convert [input_file] [output_dir] [--file-type] [--converter]
|
|||
| `--file-type`, `-t` <Tag variant="new">2.1</Tag> | option | Type of file to create (see below). |
|
||||
| `--converter`, `-c` <Tag variant="new">2</Tag> | option | Name of converter to use (see below). |
|
||||
| `--n-sents`, `-n` | option | Number of sentences per document. |
|
||||
| `--seg-sents`, `-s` <Tag variant="new">2.2</Tag> | flag | Segment sentences (for `-c ner`) |
|
||||
| `--model`, `-b` <Tag variant="new">2.2</Tag> | option | Model for parser-based sentence segmentation (for `-s`) |
|
||||
| `--morphology`, `-m` | option | Enable appending morphology to tags. |
|
||||
| `--lang`, `-l` <Tag variant="new">2.1</Tag> | option | Language code (if tokenizer required). |
|
||||
| `--help`, `-h` | flag | Show help message and available arguments. |
|
||||
|
|
@ -174,10 +176,10 @@ All output files generated by this command are compatible with
|
|||
|
||||
| ID | Description |
|
||||
| ------------------------------ | --------------------------------------------------------------- |
|
||||
| `auto` | Automatically pick converter based on file extension (default). |
|
||||
| `auto` | Automatically pick converter based on file extension and file content (default). |
|
||||
| `conll`, `conllu`, `conllubio` | Universal Dependencies `.conllu` or `.conll` format. |
|
||||
| `ner` | Tab-based named entity recognition format. |
|
||||
| `iob` | IOB or IOB2 named entity recognition format. |
|
||||
| `ner` | NER with IOB/IOB2 tags, one token per line with columns separated by whitespace. The first column is the token and the final column is the IOB tag. Sentences are separated by blank lines and documents are separated by the line `-DOCSTART- -X- O O`. Supports CoNLL 2003 NER format. See [sample data](https://github.com/explosion/spaCy/tree/master/examples/training/ner_example_data). |
|
||||
| `iob` | NER with IOB/IOB2 tags, one sentence per line with tokens separated by whitespace and annotation separated by `|`, either `word|B-ENT` or `word|POS|B-ENT`. See [sample data](https://github.com/explosion/spaCy/tree/master/examples/training/ner_example_data). |
|
||||
|
||||
## Train {#train}
|
||||
|
||||
|
|
|
|||
|
|
@ -10,6 +10,7 @@
|
|||
"en_vectors_web_lg",
|
||||
"en_pytt_bertbaseuncased_lg",
|
||||
"en_pytt_robertabase_lg",
|
||||
"pytt_distilbertbaseuncased_lg",
|
||||
"en_pytt_xlnetbasecased_lg"
|
||||
],
|
||||
"example": "This is a sentence.",
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user