explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 04:10:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add docs and unify default configs for spancat and span finder

Browse Source 
* Add `allow_overlap=True` to span finder scorer
This commit is contained in:
Adriane Boyd 2023-06-02 18:20:23 +02:00
parent 9372b22d32
commit f84b59d68a
6 changed files with 407 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/pipeline/span_finder.py
View File

@ -27,8 +27,8 @@ nO = 2
[model.tok2vec.embed] [model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2" @architectures = "spacy.MultiHashEmbed.v2"
width = 96 width = 96
rows = [5000, 2000, 1000, 1000] rows = [5000, 1000, 2500, 1000]
attrs = ["ORTH", "PREFIX", "SUFFIX", "SHAPE"] attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
include_static_vectors = false include_static_vectors = false
[model.tok2vec.encode] [model.tok2vec.encode]
@ -63,23 +63,26 @@ def make_span_finder(
nlp: Language, nlp: Language,
name: str, name: str,
model: Model[Iterable[Doc], Floats2d], model: Model[Iterable[Doc], Floats2d],
scorer: Optional[Callable], spans_key: str,
threshold: float, threshold: float,
max_length: Optional[int], max_length: Optional[int],
min_length: Optional[int], min_length: Optional[int],
spans_key: str, scorer: Optional[Callable],
) -> "SpanFinder": ) -> "SpanFinder":
"""Create a SpanFinder component. The component predicts whether a token is """Create a SpanFinder component. The component predicts whether a token is
the start or the end of a potential span. the start or the end of a potential span.
model (Model[List[Doc], Floats2d]): A model instance that model (Model[List[Doc], Floats2d]): A model instance that
is given a list of documents and predicts a probability for each token. is given a list of documents and predicts a probability for each token.
threshold (float): Minimum probability to consider a prediction positive.
spans_key (str): Key of the doc.spans dict to save the spans under. During spans_key (str): Key of the doc.spans dict to save the spans under. During
initialization and training, the component will look for spans on the initialization and training, the component will look for spans on the
reference document under the same key. reference document under the same key.
threshold (float): Minimum probability to consider a prediction positive.
max_length (Optional[int]): Max length of the produced spans, defaults to None meaning unlimited length. max_length (Optional[int]): Max length of the produced spans, defaults to None meaning unlimited length.
min_length (Optional[int]): Min length of the produced spans, defaults to None meaining shortest span is length 1. min_length (Optional[int]): Min length of the produced spans, defaults to None meaining shortest span is length 1.
scorer (Optional[Callable]): The scoring method. Defaults to
Scorer.score_spans for the Doc.spans[spans_key] with overlapping
spans allowed.
""" """
return SpanFinder( return SpanFinder(
nlp, nlp,
@ -107,6 +110,7 @@ def span_finder_score(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:
"getter", lambda doc, key: doc.spans.get(key[len(attr_prefix) :], []) "getter", lambda doc, key: doc.spans.get(key[len(attr_prefix) :], [])
) )
kwargs.setdefault("has_annotation", lambda doc: key in doc.spans) kwargs.setdefault("has_annotation", lambda doc: key in doc.spans)
kwargs.setdefault("allow_overlap", True)
scores = Scorer.score_spans(examples, **kwargs) scores = Scorer.score_spans(examples, **kwargs)
scores.pop(f"{kwargs['attr']}_per_type", None) scores.pop(f"{kwargs['attr']}_per_type", None)
return scores return scores
@ -141,11 +145,11 @@ class SpanFinder(TrainablePipe):
model: Model[Iterable[Doc], Floats2d], model: Model[Iterable[Doc], Floats2d],
name: str = "span_finder", name: str = "span_finder",
*, *,
spans_key: str = DEFAULT_SPANS_KEY,
threshold: float = 0.5, threshold: float = 0.5,
max_length: Optional[int] = None, max_length: Optional[int] = None,
min_length: Optional[int] = None, min_length: Optional[int] = None,
scorer: Optional[Callable] = span_finder_score, scorer: Optional[Callable] = span_finder_score,
spans_key: str = DEFAULT_SPANS_KEY,
) -> None: ) -> None:
"""Initialize the span boundary detector. """Initialize the span boundary detector.
model (thinc.api.Model): The Thinc Model powering the pipeline component. model (thinc.api.Model): The Thinc Model powering the pipeline component.

4
spacy/pipeline/spancat.py
View File

@ -31,8 +31,8 @@ hidden_size = 128
[model.tok2vec.embed] [model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2" @architectures = "spacy.MultiHashEmbed.v2"
width = 96 width = 96
rows = [5000, 2000, 1000, 1000] rows = [5000, 1000, 2500, 1000]
attrs = ["ORTH", "PREFIX", "SUFFIX", "SHAPE"] attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
include_static_vectors = false include_static_vectors = false
[model.tok2vec.encode] [model.tok2vec.encode]

4
spacy/tests/pipeline/test_spancat.py
View File

@ -445,7 +445,7 @@ def test_overfitting_IO():
spans = doc.spans[SPAN_KEY] spans = doc.spans[SPAN_KEY]
assert len(spans) == 2 assert len(spans) == 2
assert len(spans.attrs["scores"]) == 2 assert len(spans.attrs["scores"]) == 2
assert min(spans.attrs["scores"]) > 0.9 assert min(spans.attrs["scores"]) > 0.8
assert set([span.text for span in spans]) == {"London", "Berlin"} assert set([span.text for span in spans]) == {"London", "Berlin"}
assert set([span.label_ for span in spans]) == {"LOC"} assert set([span.label_ for span in spans]) == {"LOC"}
@ -457,7 +457,7 @@ def test_overfitting_IO():
spans2 = doc2.spans[SPAN_KEY] spans2 = doc2.spans[SPAN_KEY]
assert len(spans2) == 2 assert len(spans2) == 2
assert len(spans2.attrs["scores"]) == 2 assert len(spans2.attrs["scores"]) == 2
assert min(spans2.attrs["scores"]) > 0.9 assert min(spans2.attrs["scores"]) > 0.8
assert set([span.text for span in spans2]) == {"London", "Berlin"} assert set([span.text for span in spans2]) == {"London", "Berlin"}
assert set([span.label_ for span in spans2]) == {"LOC"} assert set([span.label_ for span in spans2]) == {"LOC"}

21
website/docs/api/spancategorizer.mdx
View File

@ -105,7 +105,7 @@ architectures and their arguments and hyperparameters.
> >
> # Construction via add_pipe with custom model > # Construction via add_pipe with custom model
> config = {"model": {"@architectures": "my_spancat"}} > config = {"model": {"@architectures": "my_spancat"}}
> parser = nlp.add_pipe("spancat", config=config) > spancat = nlp.add_pipe("spancat", config=config)
> >
> # Construction from class > # Construction from class
> from spacy.pipeline import SpanCategorizer > from spacy.pipeline import SpanCategorizer
@ -524,3 +524,22 @@ has two columns, indicating the start and end position.
| `min_size` | The minimal phrase lengths to suggest (inclusive). ~~[int]~~ | | `min_size` | The minimal phrase lengths to suggest (inclusive). ~~[int]~~ |
| `max_size` | The maximal phrase lengths to suggest (exclusive). ~~[int]~~ | | `max_size` | The maximal phrase lengths to suggest (exclusive). ~~[int]~~ |
| **CREATES** | The suggester function. ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ | | **CREATES** | The suggester function. ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ |
### spacy.preset_spans_suggester.v1 {id="preset_spans_suggester"}
> #### Example Config
>
> ```ini
> [components.spancat.suggester]
> @misc = "spacy.preset_spans_suggester.v1"
> spans_key = "my_spans"
> ```
Suggest all spans that are already stored in doc.spans[spans_key]. This is
useful when an upstream component is used to set the spans on the Doc such as a
[`SpanRuler`](/api/spanruler) or [`SpanFinder`](/api/spanfinder).
| Name | Description |
| ----------- | ----------------------------------------------------------------------------- |
| `spans_key` | Key of [`Doc.spans`](/api/doc/#spans) that provides spans to suggest. ~~str~~ |
| **CREATES** | The suggester function. ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ |

372
website/docs/api/spanfinder.mdx Normal file
View File

@ -0,0 +1,372 @@
---
title: SpanFinder
tag: class,experimental
source: spacy/pipeline/span_finder.py
version: 3.6
teaser:
'Pipeline component for identifying potentially overlapping spans of text'
api_base_class: /api/pipe
api_string_name: span_finder
api_trainable: true
---
The span finder identifies potentially overlapping, unlabeled spans. It
identifies tokens that start or end spans and annotates unlabeled spans between
starts and ends, with optional filters for min and max span length. It is
intended for use in combination with a component like
[`SpanCategorizer`](/api/spancategorizer) that may further filter or label the
spans. Predicted spans will be saved in a [`SpanGroup`](/api/spangroup) on the
doc under `doc.spans[spans_key]`, where `spans_key` is a component config
setting.
## Assigned Attributes {id="assigned-attributes"}
Predictions will be saved to `Doc.spans[spans_key]` as a
[`SpanGroup`](/api/spangroup).
`spans_key` defaults to `"sc"`, but can be passed as a parameter. The
`span_finder` component will overwrite any existing spans under the spans key
`doc.spans[spans_key]`.
| Location | Value |
| ---------------------- | ---------------------------------- |
| `Doc.spans[spans_key]` | The unlabeled spans. ~~SpanGroup~~ |
## Config and implementation {id="config"}
The default config is defined by the pipeline component factory and describes
how the component should be configured. You can override its settings via the
`config` argument on [`nlp.add_pipe`](/api/language#add_pipe) or in your
[`config.cfg` for training](/usage/training#config). See the
[model architectures](/api/architectures) documentation for details on the
architectures and their arguments and hyperparameters.
> #### Example
>
> ```python
> from spacy.pipeline.span_finder import DEFAULT_SPAN_FINDER_MODEL
> config = {
> "threshold": 0.5,
> "spans_key": "my_spans",
> "max_length": None,
> "min_length": None,
> "model": DEFAULT_SPAN_FINDER_MODEL,
> }
> nlp.add_pipe("span_finder", config=config)
> ```
| Setting | Description |
| ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | A model instance that is given a list of documents and predicts a probability for each token. ~~Model[List[Doc], Floats2d]~~ |
| `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ |
| `threshold` | Minimum probability to consider a prediction positive. Defaults to `0.5`. ~~float~~ |
| `max_length` | Max length of the produced spans, defaults to `None` meaning unlimited length. ~~Optional[int]~~ |
| `min_length` | Min length of the produced spans, defaults to `None` meaning shortest span is length 1. ~~Optional[int]~~ |
| `scorer` | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~ |
```python
%%GITHUB_SPACY/spacy/pipeline/span_finder.py
```
## SpanFinder.\_\_init\_\_ {id="init",tag="method"}
> #### Example
>
> ```python
> # Construction via add_pipe with default model
> span_finder = nlp.add_pipe("span_finder")
>
> # Construction via add_pipe with custom model
> config = {"model": {"@architectures": "my_span_finder"}}
> span_finder = nlp.add_pipe("span_finder", config=config)
>
> # Construction from class
> from spacy.pipeline import SpanFinder
> span_finder = SpanFinder(nlp.vocab, model)
> ```
Create a new pipeline instance. In your application, you would normally use a
shortcut for this and instantiate the component using its string name and
[`nlp.add_pipe`](/api/language#create_pipe).
| Name | Description |
| -------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `vocab` | The shared vocabulary. ~~Vocab~~ |
| `model` | A model instance that is given a list of documents and predicts a probability for each token. ~~Model[List[Doc], Floats2d]~~ |
| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ |
| _keyword-only_ | |
| `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ |
| `threshold` | Minimum probability to consider a prediction positive. Defaults to `0.5`. ~~float~~ |
| `max_length` | Max length of the produced spans, defaults to `None` meaning unlimited length. ~~Optional[int]~~ |
| `min_length` | Min length of the produced spans, defaults to `None` meaning shortest span is length 1. ~~Optional[int]~~ |
| `scorer` | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~ |
## SpanFinder.\_\_call\_\_ {id="call",tag="method"}
Apply the pipe to one document. The document is modified in place, and returned.
This usually happens under the hood when the `nlp` object is called on a text
and all pipeline components are applied to the `Doc` in order. Both
[`__call__`](/api/spanfinder#call) and [`pipe`](/api/spanfinder#pipe) delegate
to the [`predict`](/api/spanfinder#predict) and
[`set_annotations`](/api/spanfinder#set_annotations) methods.
> #### Example
>
> ```python
> doc = nlp("This is a sentence.")
> span_finder = nlp.add_pipe("span_finder")
> # This usually happens under the hood
> processed = span_finder(doc)
> ```
| Name | Description |
| ----------- | -------------------------------- |
| `doc` | The document to process. ~~Doc~~ |
| **RETURNS** | The processed document. ~~Doc~~ |
## SpanFinder.pipe {id="pipe",tag="method"}
Apply the pipe to a stream of documents. This usually happens under the hood
when the `nlp` object is called on a text and all pipeline components are
applied to the `Doc` in order. Both [`__call__`](/api/spanfinder#call) and
[`pipe`](/api/spanfinder#pipe) delegate to the
[`predict`](/api/spanfinder#predict) and
[`set_annotations`](/api/spanfinder#set_annotations) methods.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> for doc in span_finder.pipe(docs, batch_size=50):
> pass
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------- |
| `stream` | A stream of documents. ~~Iterable[Doc]~~ |
| _keyword-only_ | |
| `batch_size` | The number of documents to buffer. Defaults to `128`. ~~int~~ |
| **YIELDS** | The processed documents in order. ~~Doc~~ |
## SpanFinder.initialize {id="initialize",tag="method"}
Initialize the component for training. `get_examples` should be a function that
returns an iterable of [`Example`](/api/example) objects. **At least one example
should be supplied.** The data examples are used to **initialize the model** of
the component and can either be the full training data or a representative
sample. Initialization includes validating the network and
[inferring missing shapes](https://thinc.ai/docs/usage-models#validation) This
method is typically called by [`Language.initialize`](/api/language#initialize)
and lets you customize arguments it receives via the
[`[initialize.components]`](/api/data-formats#config-initialize) block in the
config.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> span_finder.initialize(lambda: examples, nlp=nlp)
> ```
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Must contain at least one `Example`. ~~Callable[[], Iterable[Example]]~~ |
| _keyword-only_ | |
| `nlp` | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~ |
## SpanFinder.predict {id="predict",tag="method"}
Apply the component's model to a batch of [`Doc`](/api/doc) objects without
modifying them.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> scores = span_finder.predict([doc1, doc2])
> ```
| Name | Description |
| ----------- | ------------------------------------------- |
| `docs` | The documents to predict. ~~Iterable[Doc]~~ |
| **RETURNS** | The model's prediction for each document. |
## SpanFinder.set_annotations {id="set_annotations",tag="method"}
Modify a batch of [`Doc`](/api/doc) objects using pre-computed scores.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> scores = span_finder.predict(docs)
> span_finder.set_annotations(docs, scores)
> ```
| Name | Description |
| -------- | ---------------------------------------------------- |
| `docs` | The documents to modify. ~~Iterable[Doc]~~ |
| `scores` | The scores to set, produced by `SpanFinder.predict`. |
## SpanFinder.update {id="update",tag="method"}
Learn from a batch of [`Example`](/api/example) objects containing the
predictions and gold-standard annotations, and update the component's model.
Delegates to [`predict`](/api/spanfinder#predict) and
[`get_loss`](/api/spanfinder#get_loss).
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> optimizer = nlp.initialize()
> losses = span_finder.update(examples, sgd=optimizer)
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------ |
| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| `drop` | The dropout rate. ~~float~~ |
| `sgd` | An optimizer. Will be created via [`create_optimizer`](#create_optimizer) if not set. ~~Optional[Optimizer]~~ |
| `losses` | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
| **RETURNS** | The updated `losses` dictionary. ~~Dict[str, float]~~ |
## SpanFinder.get_loss {id="get_loss",tag="method"}
Find the loss and gradient of loss for the batch of documents and their
predicted scores.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> scores = span_finder.predict([eg.predicted for eg in examples])
> loss, d_loss = span_finder.get_loss(examples, scores)
> ```
| Name | Description |
| -------------- | --------------------------------------------------------------------------- |
| `examples` | The batch of examples. ~~Iterable[Example]~~ |
| `spans_scores` | Scores representing the model's predictions. ~~Tuple[Ragged, Floats2d]~~ |
| **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
## SpanFinder.create_optimizer {id="create_optimizer",tag="method"}
Create an optimizer for the pipeline component.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> optimizer = span_finder.create_optimizer()
> ```
| Name | Description |
| ----------- | ---------------------------- |
| **RETURNS** | The optimizer. ~~Optimizer~~ |
## SpanFinder.use_params {id="use_params",tag="method, contextmanager"}
Modify the pipe's model to use the given parameter values.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> with span_finder.use_params(optimizer.averages):
> span_finder.to_disk("/best_model")
> ```
| Name | Description |
| -------- | -------------------------------------------------- |
| `params` | The parameter values to use in the model. ~~dict~~ |
## SpanFinder.to_disk {id="to_disk",tag="method"}
Serialize the pipe to disk.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> span_finder.to_disk("/path/to/span_finder")
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
| _keyword-only_ | |
| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
## SpanFinder.from_disk {id="from_disk",tag="method"}
Load the pipe from disk. Modifies the object in place and returns it.
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> span_finder.from_disk("/path/to/span_finder")
> ```
| Name | Description |
| -------------- | ----------------------------------------------------------------------------------------------- |
| `path` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
| _keyword-only_ | |
| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The modified `SpanFinder` object. ~~SpanFinder~~ |
## SpanFinder.to_bytes {id="to_bytes",tag="method"}
> #### Example
>
> ```python
> span_finder = nlp.add_pipe("span_finder")
> span_finder_bytes = span_finder.to_bytes()
> ```
Serialize the pipe to a bytestring.
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------- |
| _keyword-only_ | |
| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The serialized form of the `SpanFinder` object. ~~bytes~~ |
## SpanFinder.from_bytes {id="from_bytes",tag="method"}
Load the pipe from a bytestring. Modifies the object in place and returns it.
> #### Example
>
> ```python
> span_finder_bytes = span_finder.to_bytes()
> span_finder = nlp.add_pipe("span_finder")
> span_finder.from_bytes(span_finder_bytes)
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------- |
| `bytes_data` | The data to load from. ~~bytes~~ |
| _keyword-only_ | |
| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The `SpanFinder` object. ~~SpanFinder~~ |
## Serialization fields {id="serialization-fields"}
During serialization, spaCy will export several data fields used to restore
different aspects of the object. If needed, you can exclude them from
serialization by passing in the string names via the `exclude` argument.
> #### Example
>
> ```python
> data = span_finder.to_disk("/path", exclude=["vocab"])
> ```
| Name | Description |
| ------- | -------------------------------------------------------------- |
| `vocab` | The shared [`Vocab`](/api/vocab). |
| `cfg` | The config file. You usually don't want to exclude this. |
| `model` | The binary model data. You usually don't want to exclude this. |

1
website/meta/sidebars.json
View File

@ -106,6 +106,7 @@
{ "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" }, { "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" },
{ "text": "Sentencizer", "url": "/api/sentencizer" }, { "text": "Sentencizer", "url": "/api/sentencizer" },
{ "text": "SpanCategorizer", "url": "/api/spancategorizer" }, { "text": "SpanCategorizer", "url": "/api/spancategorizer" },
{ "text": "SpanFinder", "url": "/api/spanfinder" },
{ "text": "SpanResolver", "url": "/api/span-resolver" }, { "text": "SpanResolver", "url": "/api/span-resolver" },
{ "text": "SpanRuler", "url": "/api/spanruler" }, { "text": "SpanRuler", "url": "/api/spanruler" },
{ "text": "Tagger", "url": "/api/tagger" }, { "text": "Tagger", "url": "/api/tagger" },