explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-13 05:07:03 +03:00
Code Issues Packages Projects Releases Wiki Activity

more small corrections

Browse Source
This commit is contained in:
svlandeg 2020-11-20 22:29:58 +01:00
parent 5ac0867427
commit e861e928df
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
website/docs/usage/layers-architectures.md
View File

@ -644,7 +644,6 @@ that has the full implementation.
> >
> [model.create_instance_tensor.get_instances] > [model.create_instance_tensor.get_instances]
> # ... > # ...
> `
> ``` > ```
```python ```python
@ -666,7 +665,7 @@ def create_tensors(
) )
### The custom forward function # The custom forward function
def instance_forward( def instance_forward(
model: Model[List[Doc], Floats2d], model: Model[List[Doc], Floats2d],
docs: List[Doc], docs: List[Doc],
@ -686,7 +685,7 @@ def instance_forward(
return relations, backprop return relations, backprop
### The custom initialization method # The custom initialization method
def instance_init( def instance_init(
model: Model, model: Model,
X: List[Doc] = None, X: List[Doc] = None,
@ -712,6 +711,13 @@ several
[built-in pooling operators](https://thinc.ai/docs/api-layers#reduction-ops) for [built-in pooling operators](https://thinc.ai/docs/api-layers#reduction-ops) for
this purpose. this purpose.
Finally, we need a `get_instances` method that **generates pairs of entities**
that we want to classify as being related or not. As these candidate pairs are
typically formed within one document, this function takes a [`Doc`](/api/doc) as
input and outputs a `List` of `Span` tuples. For instance, the following
implementation takes any two entities from the same document, as long as they
are within a **maximum distance** (in number of tokens) of eachother:
> #### config.cfg (excerpt) > #### config.cfg (excerpt)
> >
> ```ini > ```ini
@ -721,17 +727,10 @@ this purpose.
> max_length = 100 > max_length = 100
> ``` > ```
Finally, we need a `get_instances` method that **generates pairs of entities**
that we want to classify as being related or not. As these candidate pairs are
typically formed within one document, this function takes a [`Doc`](/api/doc) as
input and outputs a `List` of `Span` tuples. For instance, the following
implementation takes any two entities from the same document, as long as they
are within a **maximum distance** (in number of tokens) of eachother:
```python ```python
### Candiate generation ### Candiate generation
@spacy.registry.misc.register("rel_instance_generator.v1") @spacy.registry.misc.register("rel_instance_generator.v1")
def create_candidate_indices(max_length: int) -> Callable[[Doc], List[Tuple[Span, Span]]]: def create_instances(max_length: int) -> Callable[[Doc], List[Tuple[Span, Span]]]:
def get_candidates(doc: "Doc") -> List[Tuple[Span, Span]]: def get_candidates(doc: "Doc") -> List[Tuple[Span, Span]]:
candidates = [] candidates = []
for ent1 in doc.ents: for ent1 in doc.ents:
@ -825,6 +824,7 @@ will predict scores for each label. We add convenience methods to easily
retrieve and add to them. retrieve and add to them.
```python ```python
### The constructor (continued)
def __init__(self, vocab, model, name="rel"): def __init__(self, vocab, model, name="rel"):
"""Create a component instance.""" """Create a component instance."""
# ... # ...