mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
5e297aa20e
* Add `TrainablePipe.{distill,get_teacher_student_loss}`
This change adds two methods:
- `TrainablePipe::distill` which performs a training step of a
student pipe on a teacher pipe, giving a batch of `Doc`s.
- `TrainablePipe::get_teacher_student_loss` computes the loss
of a student relative to the teacher.
The `distill` or `get_teacher_student_loss` methods are also implemented
in the tagger, edit tree lemmatizer, and parser pipes, to enable
distillation in those pipes and as an example for other pipes.
* Fix stray `Beam` import
* Fix incorrect import
* Apply suggestions from code review
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Apply suggestions from code review
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* TrainablePipe.distill: use `Iterable[Example]`
* Add Pipe.is_distillable method
* Add `validate_distillation_examples`
This first calls `validate_examples` and then checks that the
student/teacher tokens are the same.
* Update distill documentation
* Add distill documentation for all pipes that support distillation
* Fix incorrect identifier
* Apply suggestions from code review
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Add comment to explain `is_distillable`
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
431 lines
22 KiB
Plaintext
431 lines
22 KiB
Plaintext
---
|
|
title: SentenceRecognizer
|
|
tag: class
|
|
source: spacy/pipeline/senter.pyx
|
|
version: 3
|
|
teaser: 'Pipeline component for sentence segmentation'
|
|
api_base_class: /api/tagger
|
|
api_string_name: senter
|
|
api_trainable: true
|
|
---
|
|
|
|
A trainable pipeline component for sentence segmentation. For a simpler,
|
|
rule-based strategy, see the [`Sentencizer`](/api/sentencizer).
|
|
|
|
## Assigned Attributes {id="assigned-attributes"}
|
|
|
|
Predicted values will be assigned to `Token.is_sent_start`. The resulting
|
|
sentences can be accessed using `Doc.sents`.
|
|
|
|
| Location | Value |
|
|
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
|
|
| `Token.is_sent_start` | A boolean value indicating whether the token starts a sentence. This will be either `True` or `False` for all tokens. ~~bool~~ |
|
|
| `Doc.sents` | An iterator over sentences in the `Doc`, determined by `Token.is_sent_start` values. ~~Iterator[Span]~~ |
|
|
|
|
## 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.senter import DEFAULT_SENTER_MODEL
|
|
> config = {"model": DEFAULT_SENTER_MODEL,}
|
|
> nlp.add_pipe("senter", config=config)
|
|
> ```
|
|
|
|
| Setting | Description |
|
|
| ----------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. Defaults to [Tagger](/api/architectures#Tagger). ~~Model[List[Doc], List[Floats2d]]~~ |
|
|
| `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~ |
|
|
| `scorer` <Tag variant="new">3.2</Tag> | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for the attribute `"sents"`. ~~Optional[Callable]~~ |
|
|
| `save_activations` <Tag variant="new">4.0</Tag> | Save activations in `Doc` when annotating. Saved activations are `"probabilities"` and `"label_ids"`. ~~Union[bool, list[str]]~~ |
|
|
|
|
```python
|
|
%%GITHUB_SPACY/spacy/pipeline/senter.pyx
|
|
```
|
|
|
|
## SentenceRecognizer.\_\_init\_\_ {id="init",tag="method"}
|
|
|
|
Initialize the sentence recognizer.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> # Construction via add_pipe with default model
|
|
> senter = nlp.add_pipe("senter")
|
|
>
|
|
> # Construction via create_pipe with custom model
|
|
> config = {"model": {"@architectures": "my_senter"}}
|
|
> senter = nlp.add_pipe("senter", config=config)
|
|
>
|
|
> # Construction from class
|
|
> from spacy.pipeline import SentenceRecognizer
|
|
> senter = SentenceRecognizer(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#add_pipe).
|
|
|
|
| Name | Description |
|
|
| ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `vocab` | The shared vocabulary. ~~Vocab~~ |
|
|
| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model[List[Doc], List[Floats2d]]~~ |
|
|
| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ |
|
|
| _keyword-only_ | |
|
|
| `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~ |
|
|
| `scorer` <Tag variant="new">3.2</Tag> | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for the attribute `"sents"`. ~~Optional[Callable]~~ |
|
|
|
|
## SentenceRecognizer.\_\_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/sentencerecognizer#call) and
|
|
[`pipe`](/api/sentencerecognizer#pipe) delegate to the
|
|
[`predict`](/api/sentencerecognizer#predict) and
|
|
[`set_annotations`](/api/sentencerecognizer#set_annotations) methods.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> doc = nlp("This is a sentence.")
|
|
> senter = nlp.add_pipe("senter")
|
|
> # This usually happens under the hood
|
|
> processed = senter(doc)
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| ----------- | -------------------------------- |
|
|
| `doc` | The document to process. ~~Doc~~ |
|
|
| **RETURNS** | The processed document. ~~Doc~~ |
|
|
|
|
## SentenceRecognizer.distill {id="distill", tag="method,experimental", version="4"}
|
|
|
|
Train a pipe (the student) on the predictions of another pipe (the teacher). The
|
|
student is typically trained on the probability distribution of the teacher, but
|
|
details may differ per pipe. The goal of distillation is to transfer knowledge
|
|
from the teacher to the student.
|
|
|
|
The distillation is performed on ~~Example~~ objects. The `Example.reference`
|
|
and `Example.predicted` ~~Doc~~s must have the same number of tokens and the
|
|
same orthography. Even though the reference does not need have to have gold
|
|
annotations, the teacher could adds its own annotations when necessary.
|
|
|
|
This feature is experimental.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> teacher_pipe = teacher.add_pipe("senter")
|
|
> student_pipe = student.add_pipe("senter")
|
|
> optimizer = nlp.resume_training()
|
|
> losses = student.distill(teacher_pipe, examples, sgd=optimizer)
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `teacher_pipe` | The teacher pipe to learn from. ~~Optional[TrainablePipe]~~ |
|
|
| `examples` | Distillation examples. The reference and predicted docs must have the same number of tokens and the same orthography. ~~Iterable[Example]~~ |
|
|
| _keyword-only_ | |
|
|
| `drop` | 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 distillation. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
|
|
| **RETURNS** | The updated `losses` dictionary. ~~Dict[str, float]~~ |
|
|
|
|
## SentenceRecognizer.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/sentencerecognizer#call)
|
|
and [`pipe`](/api/sentencerecognizer#pipe) delegate to the
|
|
[`predict`](/api/sentencerecognizer#predict) and
|
|
[`set_annotations`](/api/sentencerecognizer#set_annotations) methods.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> for doc in senter.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~~ |
|
|
|
|
## SentenceRecognizer.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,
|
|
[inferring missing shapes](https://thinc.ai/docs/usage-models#validation) and
|
|
setting up the label scheme based on the data. This method is typically called
|
|
by [`Language.initialize`](/api/language#initialize).
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> senter.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]~~ |
|
|
|
|
## SentenceRecognizer.predict {id="predict",tag="method"}
|
|
|
|
Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
|
|
modifying them.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> scores = senter.predict([doc1, doc2])
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| ----------- | ------------------------------------------- |
|
|
| `docs` | The documents to predict. ~~Iterable[Doc]~~ |
|
|
| **RETURNS** | The model's prediction for each document. |
|
|
|
|
## SentenceRecognizer.set_annotations {id="set_annotations",tag="method"}
|
|
|
|
Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> scores = senter.predict([doc1, doc2])
|
|
> senter.set_annotations([doc1, doc2], scores)
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| -------- | ------------------------------------------------------------ |
|
|
| `docs` | The documents to modify. ~~Iterable[Doc]~~ |
|
|
| `scores` | The scores to set, produced by `SentenceRecognizer.predict`. |
|
|
|
|
## SentenceRecognizer.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/sentencerecognizer#predict) and
|
|
[`get_loss`](/api/sentencerecognizer#get_loss).
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> optimizer = nlp.initialize()
|
|
> losses = senter.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]~~ |
|
|
|
|
## SentenceRecognizer.rehearse {id="rehearse",tag="method,experimental",version="3"}
|
|
|
|
Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the
|
|
current model to make predictions similar to an initial model to try to address
|
|
the "catastrophic forgetting" problem. This feature is experimental.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> optimizer = nlp.resume_training()
|
|
> losses = senter.rehearse(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]~~ |
|
|
|
|
## SentenceRecognizer.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
|
|
> senter = nlp.add_pipe("senter")
|
|
> scores = senter.predict([eg.predicted for eg in examples])
|
|
> loss, d_loss = senter.get_loss(examples, scores)
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| ----------- | --------------------------------------------------------------------------- |
|
|
| `examples` | The batch of examples. ~~Iterable[Example]~~ |
|
|
| `scores` | Scores representing the model's predictions. |
|
|
| **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
|
|
|
|
## SentenceRecognizer.get_teacher_student_loss {id="get_teacher_student_loss", tag="method", version="4"}
|
|
|
|
Calculate the loss and its gradient for the batch of student scores relative to
|
|
the teacher scores.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> teacher_senter = teacher.get_pipe("senter")
|
|
> student_senter = student.add_pipe("senter")
|
|
> student_scores = student_senter.predict([eg.predicted for eg in examples])
|
|
> teacher_scores = teacher_senter.predict([eg.predicted for eg in examples])
|
|
> loss, d_loss = student_senter.get_teacher_student_loss(teacher_scores, student_scores)
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| ---------------- | --------------------------------------------------------------------------- |
|
|
| `teacher_scores` | Scores representing the teacher model's predictions. |
|
|
| `student_scores` | Scores representing the student model's predictions. |
|
|
| **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
|
|
|
|
## SentenceRecognizer.create_optimizer {id="create_optimizer",tag="method"}
|
|
|
|
Create an optimizer for the pipeline component.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> optimizer = senter.create_optimizer()
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| ----------- | ---------------------------- |
|
|
| **RETURNS** | The optimizer. ~~Optimizer~~ |
|
|
|
|
## SentenceRecognizer.use_params {id="use_params",tag="method, contextmanager"}
|
|
|
|
Modify the pipe's model, to use the given parameter values. At the end of the
|
|
context, the original parameters are restored.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> with senter.use_params(optimizer.averages):
|
|
> senter.to_disk("/best_model")
|
|
> ```
|
|
|
|
| Name | Description |
|
|
| -------- | -------------------------------------------------- |
|
|
| `params` | The parameter values to use in the model. ~~dict~~ |
|
|
|
|
## SentenceRecognizer.to_disk {id="to_disk",tag="method"}
|
|
|
|
Serialize the pipe to disk.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> senter.to_disk("/path/to/senter")
|
|
> ```
|
|
|
|
| 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]~~ |
|
|
|
|
## SentenceRecognizer.from_disk {id="from_disk",tag="method"}
|
|
|
|
Load the pipe from disk. Modifies the object in place and returns it.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> senter.from_disk("/path/to/senter")
|
|
> ```
|
|
|
|
| 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 `SentenceRecognizer` object. ~~SentenceRecognizer~~ |
|
|
|
|
## SentenceRecognizer.to_bytes {id="to_bytes",tag="method"}
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter = nlp.add_pipe("senter")
|
|
> senter_bytes = senter.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 `SentenceRecognizer` object. ~~bytes~~ |
|
|
|
|
## SentenceRecognizer.from_bytes {id="from_bytes",tag="method"}
|
|
|
|
Load the pipe from a bytestring. Modifies the object in place and returns it.
|
|
|
|
> #### Example
|
|
>
|
|
> ```python
|
|
> senter_bytes = senter.to_bytes()
|
|
> senter = nlp.add_pipe("senter")
|
|
> senter.from_bytes(senter_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 `SentenceRecognizer` object. ~~SentenceRecognizer~~ |
|
|
|
|
## 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 = senter.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. |
|