explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-24 16:24:16 +03:00
Code Issues Packages Projects Releases Wiki Activity

final fixes

Browse Source
This commit is contained in:
svlandeg 2020-11-20 22:18:53 +01:00
parent 331ec83493
commit 5ac0867427
1 changed files with 22 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
website/docs/usage/layers-architectures.md
View File

@ -567,10 +567,10 @@ def create_relation_model(...) -> Model[List[Doc], Floats2d]:
return model
```
We will adapt a **modular approach** to the definition of this relation model,
and define it as chaining two layers together: the first layer that generates an
We adapt a **modular approach** to the definition of this relation model, and
define it as chaining two layers together: the first layer that generates an
instance tensor from a given set of documents, and the second layer that
transforms the instance tensor into a final tensor holding the predictions.
transforms the instance tensor into a final tensor holding the predictions:
> #### config.cfg (excerpt)
>
@ -586,7 +586,7 @@ transforms the instance tensor into a final tensor holding the predictions.
> ```
```python
### The model architecture
### The model architecture {highlight="6"}
@spacy.registry.architectures.register("rel_model.v1")
def create_relation_model(
create_instance_tensor: Model[List[Doc], Floats2d],
@ -596,8 +596,9 @@ def create_relation_model(
return model
```
The `classification_layer` could be something like a Linear layer followed by a
logistic activation function:
The `classification_layer` could be something like a
[Linear](https://thinc.ai/docs/api-layers#linear) layer followed by a
[logistic](https://thinc.ai/docs/api-layers#logistic) activation function:
> #### config.cfg (excerpt)
>
@ -748,16 +749,6 @@ generation function.
#### Intermezzo: define how to store the relations data {#component-rel-attribute}
For our new relation extraction component, we will use a custom
[extension attribute](/usage/processing-pipelines#custom-components-attributes)
`doc._.rel` in which we store relation data. The attribute refers to a
dictionary, keyed by the **start offsets of each entity** involved in the
candidate relation. The values in the dictionary refer to another dictionary
where relation labels are mapped to values between 0 and 1. We assume anything
above 0.5 to be a `True` relation. The ~~Example~~ instances that we'll use as
training data, will include their gold-standard relation annotations in
`example.reference._.rel`.
> #### Example output
>
> ```python
@ -771,6 +762,16 @@ training data, will include their gold-standard relation annotations in
> # (6, 0): {'CAPITAL_OF': 0.01, 'LOCATED_IN': 0.13, 'UNRELATED': 0.017}
> ```
For our new relation extraction component, we will use a custom
[extension attribute](/usage/processing-pipelines#custom-components-attributes)
`doc._.rel` in which we store relation data. The attribute refers to a
dictionary, keyed by the **start offsets of each entity** involved in the
candidate relation. The values in the dictionary refer to another dictionary
where relation labels are mapped to values between 0 and 1. We assume anything
above 0.5 to be a `True` relation. The ~~Example~~ instances that we'll use as
training data, will include their gold-standard relation annotations in
`example.reference._.rel`.
```python
### Registering the extension attribute
from spacy.tokens import Doc
@ -817,11 +818,11 @@ class RelationExtractor(TrainablePipe):
...
```
Typically, the constructor defines the vocab, the Machine Learning model, and
the name of this component. Additionally, this component, just like the
`textcat` and the `tagger`, stores an internal list of labels. The ML model will
predict scores for each label. We add convenience method to easily retrieve and
add to them.
Typically, the **constructor** defines the vocab, the Machine Learning model,
and the name of this component. Additionally, this component, just like the
`textcat` and the `tagger`, stores an **internal list of labels**. The ML model
will predict scores for each label. We add convenience methods to easily
retrieve and add to them.
```python
def __init__(self, vocab, model, name="rel"):
@ -1003,7 +1004,6 @@ assigns it a name and lets you create the component with
> @architectures = "rel_model.v1"
> # ...
>
>
> [training.score_weights]
> rel_micro_p = 0.0
> rel_micro_r = 0.0