Skip to main content

Cutting-edge experimental spaCy components and features

Project description

spacy-experimental: Cutting-edge experimental spaCy components and features

This package includes experimental components and features for spaCy v3.x, for example model architectures, pipeline components and utilities.

Azure Pipelines pypi Version

Installation

Install with pip:

python -m pip install -U pip setuptools wheel
python -m pip install spacy-experimental

Using spacy-experimental

Components and features may be modified or removed in any release, so always specify the exact version as a package requirement if you're experimenting with a particular component, e.g.:

spacy-experimental==0.147.0

Then you can add the experimental components to your config or import from spacy_experimental:

[components.experimental_char_ner_tokenizer]
factory = "experimental_char_ner_tokenizer"

Components

Trainable character-based tokenizers

Two trainable tokenizers represent tokenization as a sequence tagging problem over individual characters and use the existing spaCy tagger and NER architectures to perform the tagging.

In the spaCy pipeline, a simple "pretokenizer" is applied as the pipeline tokenizer to split each doc into individual characters and the trainable tokenizer is a pipeline component that retokenizes the doc. The pretokenizer needs to be configured manually in the config or with spacy.blank():

nlp = spacy.blank(
    "en",
    config={
        "nlp": {
            "tokenizer": {"@tokenizers": "spacy-experimental.char_pretokenizer.v1"}
        }
    },
)

The two tokenizers currently reset any existing tag or entity annotation respectively in the process of retokenizing.

Character-based tagger tokenizer

In the tagger version experimental_char_tagger_tokenizer, the tagging problem is represented internally with character-level tags for token start (T), token internal (I), and outside a token (O). This representation comes from Elephant: Sequence Labeling for Word and Sentence Segmentation (Evang et al., 2013).

This is a sentence.
TIIIOTIOTOTIIIIIIIT

With the option annotate_sents, S replaces T for the first token in each sentence and the component predicts both token and sentence boundaries.

This is a sentence.
SIIIOTIOTOTIIIIIIIT

A config excerpt for experimental_char_tagger_tokenizer:

[nlp]
pipeline = ["experimental_char_tagger_tokenizer"]
tokenizer = {"@tokenizers":"spacy-experimental.char_pretokenizer.v1"}

[components]

[components.experimental_char_tagger_tokenizer]
factory = "experimental_char_tagger_tokenizer"
annotate_sents = true
scorer = {"@scorers":"spacy-experimental.tokenizer_senter_scorer.v1"}

[components.experimental_char_tagger_tokenizer.model]
@architectures = "spacy.Tagger.v1"
nO = null

[components.experimental_char_tagger_tokenizer.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"

[components.experimental_char_tagger_tokenizer.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 128
attrs = ["ORTH","LOWER","IS_DIGIT","IS_ALPHA","IS_SPACE","IS_PUNCT"]
rows = [1000,500,50,50,50,50]
include_static_vectors = false

[components.experimental_char_tagger_tokenizer.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 128
depth = 4
window_size = 4
maxout_pieces = 2

Character-based NER tokenizer

In the NER version, each character in a token is part of an entity:

T	B-TOKEN
h	I-TOKEN
i	I-TOKEN
s	I-TOKEN
 	O
i	B-TOKEN
s	I-TOKEN
	O
a	B-TOKEN
 	O
s	B-TOKEN
e	I-TOKEN
n	I-TOKEN
t	I-TOKEN
e	I-TOKEN
n	I-TOKEN
c	I-TOKEN
e	I-TOKEN
.	B-TOKEN

A config excerpt for experimental_char_ner_tokenizer:

[nlp]
pipeline = ["experimental_char_ner_tokenizer"]
tokenizer = {"@tokenizers":"spacy-experimental.char_pretokenizer.v1"}

[components]

[components.experimental_char_ner_tokenizer]
factory = "experimental_char_ner_tokenizer"
scorer = {"@scorers":"spacy-experimental.tokenizer_scorer.v1"}

[components.experimental_char_ner_tokenizer.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null

[components.experimental_char_ner_tokenizer.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"

[components.experimental_char_ner_tokenizer.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 128
attrs = ["ORTH","LOWER","IS_DIGIT","IS_ALPHA","IS_SPACE","IS_PUNCT"]
rows = [1000,500,50,50,50,50]
include_static_vectors = false

[components.experimental_char_ner_tokenizer.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 128
depth = 4
window_size = 4
maxout_pieces = 2

The NER version does not currently support sentence boundaries, but it would be easy to extend using a B-SENT entity type.

Biaffine parser

A biaffine dependency parser, similar to that proposed in [Deep Biaffine Attention for Neural Dependency Parsing](Deep Biaffine Attention for Neural Dependency Parsing) (Dozat & Manning, 2016). The parser consists of two parts: an edge predicter and an edge labeler. For example:

[components.experimental_arc_predicter]
factory = "experimental_arc_predicter"

[components.experimental_arc_labeler]
factory = "experimental_arc_labeler"

The arc predicter requires that a previous component (such as senter) sets sentence boundaries during training. Therefore, such a component must be added to annotating_components:

[training]
annotating_components = ["senter"]

The biaffine parser sample project provides an example biaffine parser pipeline.

Span Finder

The SpanFinder is a new experimental component that identifies span boundaries by tagging potential start and end tokens. It's an ML approach to suggest candidate spans with higher precision.

SpanFinder uses the following parameters:

  • threshold: Probability threshold for predicted spans.
  • predicted_key: Name of the SpanGroup the predicted spans are saved to.
  • training_key: Name of the SpanGroup the training spans are read from.
  • max_length: Max length of the predicted spans. No limit when set to 0. Defaults to 0.
  • min_length: Min length of the predicted spans. No limit when set to 0. Defaults to 0.

Here is a config excerpt for the SpanFinder together with a SpanCategorizer:

[nlp]
lang = "en"
pipeline = ["tok2vec","span_finder","spancat"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.tok2vec]
factory = "tok2vec"

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v1"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["ORTH", "SHAPE"]
rows = [5000, 2500]
include_static_vectors = false

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3

[components.span_finder]
factory = "experimental_span_finder"
threshold = 0.35
predicted_key = "span_candidates"
training_key = ${vars.spans_key}
min_length = 0
max_length = 0

[components.span_finder.scorer]
@scorers = "spacy-experimental.span_finder_scorer.v1"
predicted_key = ${components.span_finder.predicted_key}
training_key = ${vars.spans_key}

[components.span_finder.model]
@architectures = "spacy-experimental.SpanFinder.v1"

[components.span_finder.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO=2

[components.span_finder.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}

[components.spancat]
factory = "spancat"
max_positive = null
spans_key = ${vars.spans_key}
threshold = 0.5

[components.spancat.model]
@architectures = "spacy.SpanCategorizer.v1"

[components.spancat.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128

[components.spancat.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = null
nI = null

[components.spancat.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}

[components.spancat.suggester]
@misc = "spacy-experimental.span_finder_suggester.v1"
predicted_key = ${components.span_finder.predicted_key}

This package includes a spaCy project which shows how to train and use the SpanFinder together with SpanCategorizer.

Coreference Components

The CoreferenceResolver and SpanResolver are designed to be used together to build a corerefence pipeline, which allows you to identify which spans in a document refer to the same thing. Each component also includes an architecture and scorer. For more details, see their pages in the main spaCy docs.

For an example of how to build a pipeline with the components, see the example coref project.

Architectures

None currently.

Other

Tokenizers

  • spacy-experimental.char_pretokenizer.v1: Tokenize a text into individual characters.

Scorers

  • spacy-experimental.tokenizer_scorer.v1: Score tokenization.
  • spacy-experimental.tokenizer_senter_scorer.v1: Score tokenization and sentence segmentation.

Misc

Suggester functions for spancat:

Subtree suggester: Uses dependency annotation to suggest tokens with their syntactic descendants.

  • spacy-experimental.subtree_suggester.v1
  • spacy-experimental.ngram_subtree_suggester.v1

Chunk suggester: Suggests noun chunks using the noun chunk iterator, which requires POS and dependency annotation.

  • spacy-experimental.chunk_suggester.v1
  • spacy-experimental.ngram_chunk_suggester.v1

Sentence suggester: Uses sentence boundaries to suggest sentence spans.

  • spacy-experimental.sentence_suggester.v1
  • spacy-experimental.ngram_sentence_suggester.v1

The package also contains a merge_suggesters function which can be used to combine suggestions from multiple suggesters.

Here are two config excerpts for using the subtree suggester with and without the ngram functionality:

[components.spancat.suggester]
@misc = "spacy-experimental.subtree_suggester.v1"
[components.spancat.suggester]
@misc = "spacy-experimental.ngram_subtree_suggester.v1"
sizes = [1, 2, 3]

Note that all the suggester functions are registered in @misc.

Bug reports and issues

Please report bugs in the spaCy issue tracker or open a new thread on the discussion board for other issues.

Older documentation

See the READMEs in earlier tagged versions for details about components in earlier releases.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

spacy-experimental-0.6.1.tar.gz (59.0 kB view hashes)

Uploaded Source

Built Distributions

spacy_experimental-0.6.1-cp311-cp311-win_amd64.whl (560.4 kB view hashes)

Uploaded CPython 3.11 Windows x86-64

spacy_experimental-0.6.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (667.5 kB view hashes)

Uploaded CPython 3.11 manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (625.6 kB view hashes)

Uploaded CPython 3.11 manylinux: glibc 2.17+ ARM64

spacy_experimental-0.6.1-cp311-cp311-macosx_11_0_arm64.whl (688.5 kB view hashes)

Uploaded CPython 3.11 macOS 11.0+ ARM64

spacy_experimental-0.6.1-cp311-cp311-macosx_10_9_x86_64.whl (720.7 kB view hashes)

Uploaded CPython 3.11 macOS 10.9+ x86-64

spacy_experimental-0.6.1-cp310-cp310-win_amd64.whl (559.8 kB view hashes)

Uploaded CPython 3.10 Windows x86-64

spacy_experimental-0.6.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (669.1 kB view hashes)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (627.3 kB view hashes)

Uploaded CPython 3.10 manylinux: glibc 2.17+ ARM64

spacy_experimental-0.6.1-cp310-cp310-macosx_11_0_arm64.whl (702.8 kB view hashes)

Uploaded CPython 3.10 macOS 11.0+ ARM64

spacy_experimental-0.6.1-cp310-cp310-macosx_10_9_x86_64.whl (739.3 kB view hashes)

Uploaded CPython 3.10 macOS 10.9+ x86-64

spacy_experimental-0.6.1-cp39-cp39-win_amd64.whl (570.3 kB view hashes)

Uploaded CPython 3.9 Windows x86-64

spacy_experimental-0.6.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (673.8 kB view hashes)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (633.1 kB view hashes)

Uploaded CPython 3.9 manylinux: glibc 2.17+ ARM64

spacy_experimental-0.6.1-cp39-cp39-macosx_11_0_arm64.whl (705.0 kB view hashes)

Uploaded CPython 3.9 macOS 11.0+ ARM64

spacy_experimental-0.6.1-cp39-cp39-macosx_10_9_x86_64.whl (741.2 kB view hashes)

Uploaded CPython 3.9 macOS 10.9+ x86-64

spacy_experimental-0.6.1-cp38-cp38-win_amd64.whl (572.6 kB view hashes)

Uploaded CPython 3.8 Windows x86-64

spacy_experimental-0.6.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (688.8 kB view hashes)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (644.9 kB view hashes)

Uploaded CPython 3.8 manylinux: glibc 2.17+ ARM64

spacy_experimental-0.6.1-cp38-cp38-macosx_11_0_arm64.whl (689.5 kB view hashes)

Uploaded CPython 3.8 macOS 11.0+ ARM64

spacy_experimental-0.6.1-cp38-cp38-macosx_10_9_x86_64.whl (719.5 kB view hashes)

Uploaded CPython 3.8 macOS 10.9+ x86-64

spacy_experimental-0.6.1-cp37-cp37m-win_amd64.whl (559.5 kB view hashes)

Uploaded CPython 3.7m Windows x86-64

spacy_experimental-0.6.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (663.8 kB view hashes)

Uploaded CPython 3.7m manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (627.8 kB view hashes)

Uploaded CPython 3.7m manylinux: glibc 2.17+ ARM64

spacy_experimental-0.6.1-cp37-cp37m-macosx_10_9_x86_64.whl (707.5 kB view hashes)

Uploaded CPython 3.7m macOS 10.9+ x86-64

spacy_experimental-0.6.1-cp36-cp36m-win_amd64.whl (620.2 kB view hashes)

Uploaded CPython 3.6m Windows x86-64

spacy_experimental-0.6.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (663.4 kB view hashes)

Uploaded CPython 3.6m manylinux: glibc 2.17+ x86-64

spacy_experimental-0.6.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (626.7 kB view hashes)

Uploaded CPython 3.6m manylinux: glibc 2.17+ ARM64

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page