explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6128 from svlandeg/fix/nr_features

Browse Source
This commit is contained in:
Ines Montani 2020-09-23 19:38:19 +02:00 committed by GitHub
commit cea9431a04
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 53 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/cli/templates/quickstart_training.jinja
View File

@ -59,7 +59,8 @@ factory = "parser"
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = false
@ -79,7 +80,8 @@ factory = "ner"
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
@ -183,7 +185,8 @@ factory = "parser"
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = true
@ -200,7 +203,8 @@ factory = "ner"
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 6
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true

2
spacy/errors.py
View File

@ -480,6 +480,8 @@ class Errors:
E201 = ("Span index out of range.")
# TODO: fix numbering after merging develop into master
E917 = ("Received invalid value {value} for 'state_type' in "
"TransitionBasedParser: only 'parser' or 'ner' are valid options.")
E918 = ("Received invalid value for vocab: {vocab} ({vocab_type}). Valid "
"values are an instance of spacy.vocab.Vocab or True to create one"
" (default).")

32
spacy/ml/models/parser.py
View File

@ -2,6 +2,7 @@ from typing import Optional, List
from thinc.api import Model, chain, list2array, Linear, zero_init, use_ops
from thinc.types import Floats2d
from ...errors import Errors
from ...compat import Literal
from ...util import registry
from .._precomputable_affine import PrecomputableAffine
@ -12,7 +13,8 @@ from ...tokens import Doc
@registry.architectures.register("spacy.TransitionBasedParser.v1")
def build_tb_parser_model(
tok2vec: Model[List[Doc], List[Floats2d]],
nr_feature_tokens: Literal[3, 6, 8, 13],
state_type: Literal["parser", "ner"],
extra_state_tokens: bool,
hidden_width: int,
maxout_pieces: int,
use_upper: bool = True,
@ -41,20 +43,12 @@ def build_tb_parser_model(
tok2vec (Model[List[Doc], List[Floats2d]]):
Subnetwork to map tokens into vector representations.
nr_feature_tokens (int): The number of tokens in the context to use to
construct the state vector. Valid choices are 3, 6, 8 and 13. The
8 and 13 feature sets are designed for the parser, while the 3 and 6
feature sets are designed for the NER. The recommended feature sets are
3 for NER, and 8 for the dependency parser.
TODO: This feature should be split into two, state_type: ["deps", "ner"]
and extra_state_features: [True, False]. This would map into:
(deps, False): 8
(deps, True): 13
(ner, False): 3
(ner, True): 6
state_type (str):
String value denoting the type of parser model: "parser" or "ner"
extra_state_tokens (bool): Whether or not to use additional tokens in the context
to construct the state vector. Defaults to `False`, which means 3 and 8
for the NER and parser respectively. When set to `True`, this would become 6
feature sets (for the NER) or 13 (for the parser).
hidden_width (int): The width of the hidden layer.
maxout_pieces (int): How many pieces to use in the state prediction layer.
Recommended values are 1, 2 or 3. If 1, the maxout non-linearity
@ -69,8 +63,14 @@ def build_tb_parser_model(
Usually inferred from data at the beginning of training, or loaded from
disk.
"""
if state_type == "parser":
nr_feature_tokens = 13 if extra_state_tokens else 8
elif state_type == "ner":
nr_feature_tokens = 6 if extra_state_tokens else 3
else:
raise ValueError(Errors.E917.format(value=state_type))
t2v_width = tok2vec.get_dim("nO") if tok2vec.has_dim("nO") else None
tok2vec = chain(tok2vec, list2array(), Linear(hidden_width, t2v_width),)
tok2vec = chain(tok2vec, list2array(), Linear(hidden_width, t2v_width))
tok2vec.set_dim("nO", hidden_width)
lower = PrecomputableAffine(
nO=hidden_width if use_upper else nO,

3
spacy/pipeline/dep_parser.pyx
View File

@ -15,7 +15,8 @@ from ..training import validate_examples
default_model_config = """
[model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
state_type = "parser"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2

3
spacy/pipeline/ner.pyx
View File

@ -13,7 +13,8 @@ from ..training import validate_examples
default_model_config = """
[model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 6
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2

13
spacy/tests/serialize/test_serialize_config.py
View File

@ -67,7 +67,8 @@ width = ${components.tok2vec.model.width}
parser_config_string = """
[model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
state_type = "parser"
extra_state_tokens = false
hidden_width = 66
maxout_pieces = 2
@ -95,7 +96,11 @@ def my_parser():
MaxoutWindowEncoder(width=321, window_size=3, maxout_pieces=4, depth=2),
)
parser = build_tb_parser_model(
tok2vec=tok2vec, nr_feature_tokens=8, hidden_width=65, maxout_pieces=5
tok2vec=tok2vec,
state_type="parser",
extra_state_tokens=True,
hidden_width=65,
maxout_pieces=5,
)
return parser
@ -345,8 +350,8 @@ def test_config_auto_fill_extra_fields():
def test_config_validate_literal():
nlp = English()
config = Config().from_str(parser_config_string)
config["model"]["nr_feature_tokens"] = 666
config["model"]["state_type"] = "nonsense"
with pytest.raises(ConfigValidationError):
nlp.add_pipe("parser", config=config)
config["model"]["nr_feature_tokens"] = 13
config["model"]["state_type"] = "ner"
nlp.add_pipe("parser", config=config)

22
website/docs/api/architectures.md
View File

@ -414,7 +414,8 @@ one component.
> ```ini
> [model]
> @architectures = "spacy.TransitionBasedParser.v1"
> nr_feature_tokens = 6
> state_type = "ner"
> extra_state_tokens = false
> hidden_width = 64
> maxout_pieces = 2
>
@ -446,15 +447,16 @@ consists of either two or three subnetworks:
state representation. If not present, the output from the lower model is used
as action scores directly.
| Name | Description |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tok2vec` | Subnetwork to map tokens into vector representations. ~~Model[List[Doc], List[Floats2d]]~~ |
| `nr_feature_tokens` | The number of tokens in the context to use to construct the state vector. Valid choices are `3`, `6`, `8` and `13`. The `8` and `13` feature sets are designed for the parser, while the `3` and `6` feature sets are designed for the entity recognizer. The recommended feature sets are `3` for NER, and `8` for the dependency parser. ~~int~~ |
| `hidden_width` | The width of the hidden layer. ~~int~~ |
| `maxout_pieces` | How many pieces to use in the state prediction layer. Recommended values are `1`, `2` or `3`. If `1`, the maxout non-linearity is replaced with a [`Relu`](https://thinc.ai/docs/api-layers#relu) non-linearity if `use_upper` is `True`, and no non-linearity if `False`. ~~int~~ |
| `use_upper` | Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to `False` for large pretrained models such as transformers, and `True` for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. ~~bool~~ |
| `nO` | The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. ~~int~~ |
| **CREATES** | The model using the architecture. ~~Model[List[Docs], List[List[Floats2d]]]~~ |
| Name | Description |
| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tok2vec` | Subnetwork to map tokens into vector representations. ~~Model[List[Doc], List[Floats2d]]~~ |
| `state_type` | Which task to extract features for. Possible values are "ner" and "parser". ~~str~~ |
| `extra_state_tokens` | Whether to use an expanded feature set when extracting the state tokens. Slightly slower, but sometimes improves accuracy slightly. Defaults to `False`. ~~bool~~ |
| `hidden_width` | The width of the hidden layer. ~~int~~ |
| `maxout_pieces` | How many pieces to use in the state prediction layer. Recommended values are `1`, `2` or `3`. If `1`, the maxout non-linearity is replaced with a [`Relu`](https://thinc.ai/docs/api-layers#relu) non-linearity if `use_upper` is `True`, and no non-linearity if `False`. ~~int~~ |
| `use_upper` | Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to `False` for large pretrained models such as transformers, and `True` for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. ~~bool~~ |
| `nO` | The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. ~~int~~ |
| **CREATES** | The model using the architecture. ~~Model[List[Docs], List[List[Floats2d]]]~~ |
## Tagging architectures {#tagger source="spacy/ml/models/tagger.py"}

3
website/docs/usage/embeddings-transformers.md
View File

@ -448,7 +448,8 @@ factory = "ner"
[nlp.pipeline.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
state_type = "ner"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = false